Machine learning prediction models for the popularization and dissemination of medical science popularization videos

Machine learning prediction models for the popularization and dissemination of medical science popularization videos | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Machine learning prediction models for the popularization and dissemination of medical science popularization videos Nuo Cheng, Xiu-Ling Wang, Yang Mu, Hui-Jun Li, Yan-Ning Ma, Yonghui Yuan, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4742337/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective To summarize the current shooting trends of this type of video, discuss the effect of non-medical factors on the spread of videos, and develop prediction models using machine learning (ML) algorithms. Methods We searched and filtered medical science popularization videos on TikTok, then labeled non-medical features as variables and record the number of “Thumb-Up”, “Comment”, “Share” and “Collection” as outcome indicators. A total of 286 samples and 34 variables were included in the construction of the ML model, and 13 algorithms were employed with the area under the curve (AUC) for performance assessment and a ten-fold cross-validation for accuracy testing. Results In the quantitative analysis of the 4 outcome indicators, we identified significant disparities among different videos. Subsequently, five best-performing models were ultimately confirmed to predict the reasons for differences: “Thumb-Up” RF Model (AUC = 0.7331), “Collection” RF Model (AUC = 0.7439), “Share” RF Model (AUC = 0.7077), “Comment” RF Model (AUC = 0.7960), “Comment” BNB Model (AUC = 0.7844). By ML models, the video duration, title and description length, shooting location emerged and body language as the most five crucial parameters across all five models. Conclusion ML models demonstrated superior performance in predicting the influence of non-medical factors on the spread of medical science popularization videos. The weight of these variables will provide valuable guidance for video preparation. This study contributes to the dissemination and acceptance of medical science popularization videos by the public, thereby promoting health education and enhancing public awareness and competence in healthcare. Health sciences/Health care Health sciences/Health care/Health services Health sciences/Health care/Public health Machine learning Medical science popularization short videos Prediction models Non-medical factors Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 1 Introduction In the digital age, medical science popularization videos have become a powerful tool for widely disseminating medical knowledge and information. These videos provide the public with crucial insights into health, disease, and medical technology, thereby promoting public health literacy and behavior [ 1 , 2 ]. TikTok, as one of the most well-known short video platforms all over the world, known for its short and engaging video format. TikTok boasts over 750 million daily active users in China[ 3 ]. Compared with traditional information dissemination methods, short videos in TikTok have many advantages, including stronger visibility, attractiveness, interactivity and faster transmission speed, which makes it an emerging medical science popularization videos center[ 4 ]. The dissemination of these videos helps to narrow the gap between medical professionals and the public, providing short, accessible insights into complex medical topics[ 5 ]. In the dissemination process of medical science popularization videos, it is not only necessary to ensure the reliability and authenticity of the content[ 6 , 7 ], but also some non-medical factors can significantly affect the dissemination and attractiveness, such as video production quality, animation, visual aids, and the ability to simplify complex topics contribute to the overall appeal, accessibility of the video and so on[ 8 ]. Compared to the professionalism of medical information, these non-medical factors often play a undeniable role[ 9 ]. Therefore, by analyzing these non-medical factors, it is possible to predict and promote the dissemination intensity and effectiveness of medical science popularization videos. Currently, there are few studies specifically targeting these non-medical factors. In recent times, machine learning (ML) models, including but not limited to Decision Tree (DT), Random Forest (RF), have concerned widely because of their outstanding predictive abilities. In contrast to traditional multiple logistic regression (LR) models, ML models operate based on novel logical paradigms, which can more effectively utilize data, and showing enhanced predictive performance on diverse critical fields such as predicting High-risk factors, key feature variables and so on. ML has emerged as a cutting-edge technology for predictive modeling and decision-making[ 10 , 11 ], providing a promising strategy for constructing influence prediction models for science popularization videos before their release. To this end, this study was designed to search for medical science popularization videos on the TikTok platform, extract non-medical professional feature parameters, conduct a statistical analysis of their distribution characteristics, and subsequently develop and validate ML models for four influence outcome metrics (Thumb-Up, Comment, Share and Collection). 2 Methods 2.1 Study subjects We used “medical science popularization” as the keyword to search on the TikTok platform ( https://www.TikTok.com/ ) from January to March 2023. Inclusion criteria: 1) The video published by tertiary A hospitals or above; 2) The theme is related to medical science popularization, health education, prevention and treatment, and nursing. Exclusion criteria: The content is repetitive, non-original, commercial, incorrect and involves advertising. A manual review process was employed by two doctors independently. Finally, 286 videos were included, and the video screening process is shown in Fig. 1 . 2.2 Data collection Two doctors extracted information from the video independently. The variables are categorized into three aspects: host characteristics, shooting methods, production and publication (Supplementary Table) . In addition, we collected the number of “Thumb-Up”, “Comment”, “Share” and “Collection” for each video, which as indicators for evaluating the effectiveness of video dissemination. 2.3 ML prediction models construction A total of 286 samples and 34 variables were included in the construction of the ML predictive models by using the Dr. Wise multimodal research platform ( https://keyan.deepwise.com/ ), which is underpinned by Python 3.6 and integrates models from the scikit-learn library (version 0.21.2). Image-related processing was carried out using scikit-image (version 0.16.2)[ 12 ]. The platform facilitates ML modeling through visualized configuration, encompassing variable setup, partitioning of training and testing datasets, feature engineering (feature cleaning and selection), and model hyperparameter tuning. Once the parameters are configured, the platform invokes Python for model implementation and chart outputs. Based on the distinct distribution characteristics of the data ( Supplementary Table ), the median of each outcome was calculated and utilized as cutoff value of binary classification, to construct four types of ML prediction models (Thumb-Up, Collection, Share and Comment). Thirteen classification algorithms were employed to select predictive models, including Decision Tree (DT), K Nearest Neighbors (KNN), Linear Support Vector Classifier (LSVC), Random Forest (RF), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Gradient Boosting, Bernoulli Naive Bayes (NB), Stochastic Gradient Descent (SGD), AdaBoost, XG Boost (XGB), Gaussian Naive Bayes (NB), Logistic Regression (LR). A 7:3 random split for the entire cohort was repeated 6 times, forming 6 pairs of training and validation sets, for 6 constructions of each algorithm model respectively. For feature dimensionality reduction, two methods were employed: feature correlation analysis and L1 regularization-based feature selection. If the correlation coefficient between features was greater than 0.9, one of the correlated features was retained (feature correlation analysis). L1 regularization-based feature selection involved building a linear model on the training data to obtain a sparse coefficient matrix, whereby features with higher absolute coefficient values were more likely to be retained. The parameter "C" controlled the stringency of feature selection; a smaller "C" retained fewer features. Following feature selection, the optimal parameters were determined using grid search and the ML models were trained and validated. The preliminary evaluation and comparison of model performance were preformed through averaging the 6 results of area under the curve (AUC), and subsequently a ten-fold cross-validation of the preliminary candidate models was performed for further validation and final confirmation of the best-performing models. Thereafter, the obtained optimal models will be published on the Dr. Wise multimodal research platform at https://keyan.deepwise.com/ (Authorization login required; individuals with prediction and validation needs are encouraged to contact the corresponding author). The platform supports external validation through queuing and allows for predicting the psychological state of individual subjects. 2.4 Statistical methods The statistical analyses were conducted with SPSS (version 26.0, SPSS, Chicago, IL, USA) and the Dr. Wise multimodal research platform ( https://keyan.deepwise.com/ ). Normally distributed data were presented as mean with standard deviation. Non-normally distributed data were expressed as medians (interquartile range [IQR]). Categorical data is represented by the number of examples and rate (%). Multivariate logistic analysis was used to screen the associated factors. A significance level of P < 0.05 (two-tailed) was considered to indicate statistically significant differences. 3 Results 3.1 General information description Among 286 videos, the minimum and maximum numbers of “Thumb-Up” are 0 and 2.72 million respectively, with an average of 1.46 million ± 3.61 million. The minimum and maximum numbers of “Collection” are 1 and 0.14 million respectively, with an average of 0.03 million ± 0.11 million. The minimum and maximum numbers of “Share” are 4 and 898 thousand respectively, with an average of 40.57 thousand ± 86.39 thousand. The minimum and maximum numbers of “Comment” are 0 and 200 thousand respectively, with an average of 7.70 thousand ± 20.47 thousand. The four metrics were categorized into high and low groups based on their respective medians, effectively converting continuous variables into binary outcome variables. The median values are 30 thousand (Thumb-Up), 5846 (Collection), 9113 (Share), and 1113.5 (Comment). In terms of host characteristics, the anchors of videos are mainly male, with chief physicians and more specialties in internal medicine. They mostly wear doctor’s gown, with no make-up, who are expressive and have more body language. In terms of shooting techniques, videos are often shot from the front of a fixed vertical screen in close range under ambient light, with one person in the majority, often in the department office. In terms of video production and publication, most videos do not have background music, animation effects, beauty effects, and stickers, but have prompts and name bar. The publication time is mostly from 17:00 to 19:00 ( Supplementary Table ). There is a positive correlation among the four outcome indicators, and the difference is statistically significant ( Table 1 ). 3.2 Comparison of various prediction models Based on the results of AUC comparison, we identified 8 candidate models in the preliminary stage, comprising 1 for Thumb-Up ( Figure 2 A ), 2 for Collection ( Figure 2 B ), 2 for Share ( Figure 2 C ), 3 for Comment ( Figure 2 D ). Subsequently, one model was excluded from each of the last three types, due to substandard calibration curves or decision curves ( Supplementary Figure 1 ). The five ultimately confirmed best-performing models, predicting the four outcomes, exhibited robust discriminative capabilities, as supported by their respective confusion matrices and ROC curves: “Thumb-Up” RF Model (AUC=0.7331, Figure 3 A&B ), “Collection” RF Model (AUC=0.7439, Figure 4 A&B ), “Share” RF Model (AUC=0.7077, Figure 5 A&B ), “Comment” RF Model (AUC=0.7960, Figure 6 A&B ), “Comment” BNB Model (AUC=0.7844, Figure 7 A&B ). Moreover, their Precision-Recall (P-R) curves provide additional validation to the observed robust discriminative ability (the subfigures C of Figure 3 to 7, respectively). As depicted in Table 2, the detailed accuracy, sensitivity, specificity, precision, and F1 score for each model highlight their exceptional performance in terms of a more comprehensive presentation, although certain values exhibit an unstable performance, such as the specificity in “Share” RF Model (0.6163, 95%CI: 0.5601-0.6724). These indications imply that the overall performances of these models are consistent and satisfactory. In terms of calibration, the good overall predictive accuracy of the five models was substantiated by their respective Brier Scores (0.1693, 0.1696, 0.0619, 0.1757, 0.1808, all of which are below 0.25). This affirmation was further supported by visual predictive score charts and the calibration curves (the subfigures E&F of Figure 3 to 7, respectively). Additionally, the decision curves have also delineated a substantial net benefit within all ML prediction models (the subfigures G of Figure 3 to 7, respectively). These indicate that these models have significant value in the prediction and decision-making process, and their predictive outcomes can positively influence decision-making. 3.3 Parameter weight analysis results As revealed by the analysis of parameter weights, the video duration, title and description length, shooting location, moderate body Language, emerged as the most five crucial parameters across all five models. Other factors varied in importance across different models (the subfigures H of Figure 3 to 7, respectively). The further multivariable logistic regression analysis shows that the video duration, the length of videos description can promote video’s dissemination and influence, Less and more body language are factors in promoting all outcomes, while no and moderate body language are hindrance. The factors that hinder public sharing also include make-up. Male, emergency and surgical professionals, abundant and serious facial expressions, side and oblique side shots are factors that promote public comments. Internal medicine and traditional Chinese medicine, make-up, more and normal facial expressions, and front angle shooting are factors that hinder comments ( Table 3 ). Combining the results of descriptive statistics, ML weight analysis, and multivariable logistic regression analysis, we confirmed the trends of factors that promote or impede Thumb-Up, Collection, Share, and Comment ( Table 3 and Table 4 ). 4 Discussion In this study, we summarized the current shooting trends of medical science popularization short videos, including host characteristics and commonly used shooting and production techniques, to enhance the understanding of medical scientific information dissemination on this emerging communication platform. Based on these non-medical factors, for the first time, we developed and validated five ML models for predicting the influence of these videos, achieving precise predictions prior to their release. More importantly, these models identified the significance of different influencing factors, providing guidance for the entire video production process. Therefore, this study will help improve public awareness of medical knowledge by elucidating how these factors interact and collectively affect the popularity and dissemination speed of medical content. By enhancing the popularity and dissemination likelihood of these videos, our study is expected to increase the impact of medical science popularization efforts, thereby contributing to the improvement of public health literacy. It is necessary and meaningful to study the non-medical factors of medical education video through the TikTok. TikTok has become a vital video platform for sharing fascinating scientific knowledge[ 13 ]. More and more health care professionals use the TikTok to convey important health information to the public, and more research focuses on the analysis of medical care professional video content and form on TikTok[ 14 – 16 ]. Du et al[ 17 ] explored the content and quality of videos on the TikTok and Bilibili platforms, and analyzed the relationship with the number of views, comments, shares, and favorites. Rudisill et al[ 18 ] and wang et al[ 19 ] evaluated the reliability and educational quality of videos and found that longer video durations predicted higher scores, the former show that there is no independent correlation between the uploaded source or content and quality score, while the latter show that academic and clinical sources can lead to the higher video quality. A study noted the influence of non-medical factors such as video style, original music by analyzing the likes, comments, and reposts of the top 100 most popular micro-videos[ 16 ]. Li et al[ 20 ] investigate how the video attributes (video format, type and content) are related to quantitative indicators of user engagement (numbers of views, likes, comments and shares). Although these studies suggest that non-medical factors may be key to attracting the public to watch videos, there has few studies focused exclusively on these non-medical factors. Therefore, this study controlled for consistency in professionalism and quality to observe the impact of non-medical factors on the four influence indicators. The results further directly demonstrate the critical role of non-medical factors. The significant differences in views, likes, shares, and collections between videos caused by non-medical factors suggest that these factors may have a more decisive influence than the video's professionalism and quality. This can be primarily explained by the fact that the audience often lacks expertise in medical knowledge, making them likely to overlook medical professionalism and instead rely on non-medical factors to judge whether a science popularization video is worth watching and sharing. From a methodological perspective, analyzing video health communication is currently widely based on content analysis methods[ 16 , 21 ]. Some studies also use multivariate linear analysis based on traditional statistics to explore the factors related to video quality and associated factors[ 22 , 23 ]. However, referring to the development of medical big data mining research, these methods have significant limitations in exploring the complex nonlinear relationships commonly present among data[ 24 ]. In recent times, ML has emerged as a cutting-edge technology for predictive modeling and decision-making, substantially enhancing the precision of outcome predictions[ 25 ]. Additionally, ML model can distinguish the importance of different variables, and avoid the one-sided and subjective observation of a single indicator alone[ 26 ]. Therefore, it has been widely applied in the development of predictive models across various research domains[ 27 – 29 ]. In the field of video science popularization, ML is commonly used to analyze and evaluate public willingness[ 30 ] and emotional tendencies[ 31 , 32 ], as well as to analyze video quality[ 33 , 34 ]. For example, by using ML to identify, retrieve, and qualify medical related and understandable YouTube videos, domain experts can then review and recommend these videos for dissemination and public education[ 35 ]. Usman et al[ 36 ] proposed that ML models can effectively predict customer satisfaction from healthcare datasets. Alghamdi et al[ 37 ] used ML models for fake news detection, which demonstrate good predictive performance. In this study, we adopted the application models of ML from the field of disease prediction to explore the development of influence prediction models for medical science popularization videos, by comparing the performance of 13 commonly used ML algorithms. Finally, the FR algorithm was confirmed as the best-performing model across the four outcome indicators, while the BNB algorithm showed consistent and satisfactory performance specifically for the “Comment” outcome. These findings regarding ML algorithms are consistent with patterns reported in numerous studies[ 38 ]. Our results not only indicate that non-medical factors can predict the influence of science popularization videos, but also demonstrate that ML algorithms can significantly enhance this predictive ability. Moreover, we found that nonlinear algorithms significantly outperform traditional linear algorithms (e.g., LR), further confirming the existence of complex data relationships between non-medical factors and outcomes. We found that in terms of host characteristics, the chief physician and associate chief physician assume educational responsibilities, but the attending physician and resident physician are more popular among people. Although the chief physician and associate chief physician have more experience and expertise, lower-level physicians may be more humorous, their shooting methods or content being more vivid and interesting. Studies have shown that humor can significantly enhance user immersion and entertainment, especially when combined with medical information, thereby enhancing user acceptance[ 39 , 40 ]. People are not very interested in the image of wearing a white coat, but they are more interested in medical personnel wearing surgical gowns. At the same time, research results show that people are more interested in and pay more attention to science popularization videos of surgical professionals. Moderate Body Language is not beneficial, more body language demonstrates good effects, which can demonstrate the professionalism and affinity of host. Surprisingly, make-up does not attract attention. Although people have requirements for beauty[ 41 ], this requirement seems to not applicable to medical science popularization. In terms of Shooting techniques, the shooting location, scene, and angle have a higher weight. The video shooting in the department office is not good, while in the conference room is better. It may be because the environment of the department office is relatively noisy, the conference room is relatively quiet, resulting in better video shooting and presentation effects[ 42 ]. The dissemination effect of close-up shooting is better, and the shooting angles of the side and oblique sides are also better than those of frontal shooting. The video shoted in these methods are natural and clear, and therefore more popular among people. In terms of video production and publication, the length of video description, duration, and length of questions can all affect the dissemination and engagement. Videos on TikTok with the shortest duration received the most numbers of “likes", “comments", and “shares"[ 43 ]. Zhu et al[ 16 ] found that the presentation method of micro-video is more popular. The duration of the video should not be too long, and the title and video descriptions content should be concise, clear, and easy to understand[ 44 ]. Proper use of beauty filters is beneficial, but background music should be used with caution. Sometimes background music may give people a scripted feeling or mask some of the sound[ 45 ]. Medical videos should ensure their rigor and seriousness, and should be convincing and serious. Therefore, beauty filters should be used moderately, and appropriate background music should be chosen. The popularity and dissemination effect of videos released from 13:30 to 19:00 are better, videos released in the afternoon are more likely to be shared with others, and videos released later are more likely to receive likes. Most people are working or busy during the day, users are more likely to invest more effort for the time-consuming activity of watching the video in the evening.[ 46 ]. However, this study has certain limitations. Firstly, the videos screened in this study are in Chinese. Consequently, the findings derived from this study may not be readily applicable to videos in other languages found on TikTok. Secondly, we searched from January to March 2023 and obtained 286 samples only, which is relatively small, we will conduct larger sample studies in the future. Conclusions ML models have shown superior performance in predicting non-medical factors that affect the dissemination of medical science popularization videos, and can better demonstrate the nonlinear relationships between factors. In addition to the reliability and authenticity of medical science popularization videos, the following points should also be noted. The duration of the video should be short, and the title and video description content should be concise and clear. The shooting location should be in the conference room. The physicians in the video should not use excessive body language or excessive make-up, but can use beauty filters in moderation. The video content should be vivid, interesting, and easier to understand. Based on our research findings, we hope to provide reference for the production and filming of short videos in the future, so that short videos can be better disseminated and accepted by the public, in order to promote health education, and enhance public awareness and ability in health care. Abbreviations ML= machine learning AUC= area under the curve DT= Decision Tree RF= Random Forest LR= logistic regression Declarations The Conflict of Interest None declared. Author contributions (1) concept and design：Nuo Cheng, Xiu-Ling Wang, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang （2）acquisition of data：Nuo Cheng, Hui-Jun Li, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang （3）analysis of data：Xiu-Ling Wang, Yang Mu, Hui-Jun Li, Yan-Ning Ma, Yonghui Yuan, Guang-Wei Zhang （4）preparation of manuscript：Nuo Cheng, Xiu-Ling Wang completed the first draft, and Nuo Cheng, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang revised it. All authors read and approved the final manuscript. Acknowledgements This work was supported by the National Key Research and Development Program of China [No. 2020YFC2006401 & 2020YFC2006406], Science and Technology Projects in Liaoning Province (2023JH2/20200056), Project of Applied Basic Research Program of Liaoning province (2023JH26/10300016), and National College Students' innovation and entrepreneurship training program (No. 202110159005). Technical assistance provided by Hangzhou Deepwise & League of PHD Technology Co., Ltd is gratefully acknowledged. Appendix A. Supplementary material Data availability Data is provided within the manuscript or supplementary information files. References Seifert, L.B., et al., #OMFSurgery: analyzing the use of social media applications in oral and maxillofacial surgery resident training. BMC Oral Health, 2023. 23 (1): p. 212. Tian, K., et al., The impact of perceived value and affection on Chinese residents' continuous use intention of mobile health science information: An empirical study. Front Public Health, 2023. 11 : p. 1034231. Liu, H., et al., Assessment of the reliability and quality of breast cancer related videos on TikTok and Bilibili: cross-sectional study in China. Front Public Health, 2023. 11 : p. 1296386. Liu, K., Research on the core competitiveness of short video industry in the context of big data—a case study of tiktok of bytedance company. American Journal of Industrial and Business Management, 2022. 12 (4): p. 699-730. Thimbleby, H., Technology and the future of healthcare. J Public Health Res, 2013. 2 (3): p. e28. O'Sullivan, N.J., et al., The unintentional spread of misinformation on 'TikTok'; A paediatric urological perspective. J Pediatr Urol, 2022. 18 (3): p. 371-375. Zhang, J., et al., Popular science and education of cosmetic surgery in China: Quality and reliability evaluation of Douyin short videos. Health Expect, 2023. 26 (3): p. 1221-1226. Montag, C., H. Yang, and J.D. Elhai, On the Psychology of TikTok Use: A First Glimpse From Empirical Findings. Front Public Health, 2021. 9 : p. 641673. Basch, C.H., et al., How TikTok Is Being Used to Help Individuals Cope With Breast Cancer: Cross-sectional Content Analysis. JMIR Cancer, 2022. 8 (4): p. e42245. Liang, Q., et al., Prediction of successful weaning from renal replacement therapy in critically ill patients based on machine learning. Ren Fail, 2024. 46 (1): p. 2319329. Zhang, Y.B., et al., Development of a machine learning-based model for predicting risk of early postoperative recurrence of hepatocellular carcinoma. World J Gastroenterol, 2023. 29 (43): p. 5804-5817. Xu, A., et al., Development and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma. BMC Cancer, 2022. 22 (1): p. 872. Comp, G., S. Dyer, and M. Gottlieb, Is TikTok The Next Social Media Frontier for Medicine? AEM Educ Train, 2021. 5 (3). Basch, C.H., et al., Deconstructing TikTok Videos on Mental Health: Cross-sectional, Descriptive Content Analysis. JMIR Form Res, 2022. 6 (5): p. e38340. Chasca, W., et al., TikTok and #OccupationalTherapy: Cross-sectional Study. JMIR Form Res, 2023. 7 : p. e45554. Zhu, C., et al., How Health Communication via Tik Tok Makes a Difference: A Content Analysis of Tik Tok Accounts Run by Chinese Provincial Health Committees. Int J Environ Res Public Health, 2019. 17 (1). Du, R.C., et al., TikTok and Bilibili as sources of information on Helicobacter pylori in China: A content and quality analysis. Helicobacter, 2023. 28 (5): p. e13007. Rudisill, S.S., et al., YouTube as a source of information on pediatric scoliosis: a reliability and educational quality analysis. Spine Deform, 2023. 11 (1): p. 3-9. Wang, H., et al., YouTube online videos as a source for patient education of cervical spondylosis-a reliability and quality analysis. BMC Public Health, 2023. 23 (1): p. 1831. Li, Y., et al., Communicating COVID-19 information on TikTok: a content analysis of TikTok videos from official accounts featured in the COVID-19 information hub. Health Educ Res, 2021. 36 (3): p. 261-271. Frohlich, D.O. and A. Zmyslinski-Seelig, The presence of social support messages on YouTube videos about inflammatory bowel disease and ostomies. Health Commun, 2012. 27 (5): p. 421-8. Kwak, D., et al., Quality and reliability evaluation of online videos on carpal tunnel syndrome: a YouTube video-based study. BMJ Open, 2022. 12 (4): p. e059239. Baker, J.D., et al., Assessing the Quality and Credibility of Publicly Available Videos on Cervical Fusion: Is YouTube a Reliable Educational Tool? Int J Spine Surg, 2021. 15 (4): p. 669-675. Byeon, H., Screening dementia and predicting high dementia risk groups using machine learning. World J Psychiatry, 2022. 12 (2): p. 204-211. Waljee, A.K. and P.D. Higgins, Machine learning in medicine: a primer for physicians. Am J Gastroenterol, 2010. 105 (6): p. 1224-6. Huang, K., et al., Random Forest Model for Labor Induction in Pregnant Women With Hypertensive Disorders Using a Cervical Double Balloon. Altern Ther Health Med, 2023. 29 (1): p. 44-51. Xiang, K., et al., TM-Score predicts immunotherapy efficacy and improves the performance of the machine learning prognostic model in gastric cancer. Int Immunopharmacol, 2024. 134 : p. 112224. Cai, Y., et al., Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review. BMC Med, 2024. 22 (1): p. 56. Pencina, M.J., B.A. Goldstein, and R.B. D'Agostino, Prediction Models - Development, Evaluation, and Clinical Application. N Engl J Med, 2020. 382 (17): p. 1583-1586. Kinugasa, Y., et al., Factors affecting the willingness of nursing care staffs for cooperation with heart failure care and the role of internet video education. J Gen Fam Med, 2024. 25 (1): p. 19-27. Asghari, M., et al., Classifying Comments on Social Media Related to Living Kidney Donation: Machine Learning Training and Validation Study. JMIR Med Inform, 2022. 10 (11): p. e37884. Zheng, C., et al., Public Opinions and Concerns Regarding the Canadian Prime Minister's Daily COVID-19 Briefing: Longitudinal Study of YouTube Comments Using Machine Learning Techniques. J Med Internet Res, 2021. 23 (2): p. e23957. Rodriguez-Rodriguez, A.M., et al., Quality Analysis of YouTube Videos Presenting Pelvic Floor Exercises after Prostatectomy Surgery. J Pers Med, 2021. 11 (9). Rodriguez Rodriguez, A.M., et al., Quality Analysis of YouTube Videos Presenting Shoulder Exercises after Breast Cancer Surgery. Breast Care (Basel), 2022. 17 (2): p. 188-198. Guo, Y., et al., YouTube Videos for Public Health Literacy? A Machine Learning Pipeline to Curate Covid-19 Videos. Stud Health Technol Inform, 2024. 310 : p. 760-764. Usman, M., et al., Analyzing patients satisfaction level for medical services using twitter data. PeerJ Comput Sci, 2024. 10 : p. e1697. Alghamdi, J., Y. Lin, and S. Luo, Towards COVID-19 fake news detection using transformer-based models. Knowl Based Syst, 2023. 274 : p. 110642. Kim, D.W., et al., Machine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report. Bone, 2018. 116 : p. 207-214. McBriar, J.D., et al., #Neurosurgery: A Cross-Sectional Analysis of Neurosurgical Content on TikTok. World Neurosurg X, 2023. 17 : p. 100137. Xu, Y., J. Wang, and M. Ma, Adapting to Lockdown: Exploring Stress Coping Strategies on Short Video Social Media During the COVID-19 Pandemic. Psychol Res Behav Manag, 2023. 16 : p. 5273-5287. Kou, L., et al., Observation for clinical effect of acupuncture combined with conventional therapy in the treatment of acne vulgaris. Medicine (Baltimore), 2020. 99 (18): p. e19764. Molavynejad, S., M. Miladinia, and M. Jahangiri, A randomized trial of comparing video telecare education vs. in-person education on dietary regimen compliance in patients with type 2 diabetes mellitus: a support for clinical telehealth Providers. BMC Endocr Disord, 2022. 22 (1): p. 116. Cai, Q.Y., et al., Quality assessment of videos on social media platforms related to gestational diabetes mellitus in China: A cross-section study. Heliyon, 2024. 10 (7): p. e29020. Rooney, M.K., et al., Readability of Patient Education Materials From High-Impact Medical Journals: A 20-Year Analysis. J Patient Exp, 2021. 8 : p. 2374373521998847. Barratt, E.L., C. Spence, and N.J. Davis, Sensory determinants of the autonomous sensory meridian response (ASMR): understanding the triggers. PeerJ, 2017. 5 : p. e3846. Connelly, Y., et al., Implementation of a Personalized Digital App for Pediatric Preanesthesia Evaluation and Education: Ongoing Usability Analysis and Dynamic Improvement Scheme. JMIR Form Res, 2022. 6 (5): p. e34129. Tables Table 1. The correlation among the four outcome indicators (N=286) Thumb-Up Collection share comment Thumb-Up Pearson correlation (r) 1 Sig.（two-tailed） Collection Pearson correlation (r) 0.350 ** 1 Sig.（two-tailed） P ＜0.01 share Pearson correlation (r) 0.308 ** 0.495 ** 1 Sig.（two-tailed） P ＜0.01 P ＜0.01 comment Pearson correlation (r) 0.728 ** 0.555 ** 0.478 ** 1 Sig.（two-tailed） P ＜0.01 P ＜0.01 P ＜0.01 ** P ＜0.01 Table 2. Analysis of predictive performance for five prediction models Prediction Models Performance (95% CI) Accuracy Sensitivity Specificity Precision F1 score “Thumb-Up” RF Model 0.6531 (0.6229-0.6833) 0.6241 (0.6023-0.6458) 0.6822 (0.63-0.7344) 0.6649 (0.6251-0.7046) 0.6432 (0.6176-0.6687) “Collection” RF Model 0.6802 (0.6446-0.7159) 0.6938 (0.6476-0.74) 0.6667 (0.6119-0.7214) 0.677 (0.6394-0.7147) 0.6842 (0.6491-0.7193) “Share” RF Model 0.6492 (0.6202-0.6783) 0.6822 (0.6437-0.7206) 0.6163 (0.5601-0.6724) 0.6419 (0.6083-0.6755) 0.6604 (0.6341-0.6866) “Comment” RF model 0.7171 (0.7019-0.7323) 0.7442 (0.7018-0.7866) 0.6899 (0.6553-0.7246) 0.7069 (0.6893-0.7245) 0.7239 (0.704-0.7438) “ Comment” BNB model 0.7093 (0.683-0.7356) 0.6706 (0.6488-0.6923) 0.7481 (0.705-0.7912) 0.7286 (0.6927-0.7644) 0.6979 (0.6738-0.7219) Table 3. parameters in the multivariable logistic regression model Characteristics Thumb-Up Collection Share Comment P OR P OR P OR P OR ↑Video duration 0.001** 1.009(1.003～1.014) 0.001** 1.008(1.003～1.013) 0.003** 1.007(1.002～1.012) 0.003** 1.009(1.003～1.015) ↑Video description length 0.006** 1.046(1.013～1.080) 0.004** 1.058(1.018～1.100) ↓With prompt 0.023* 2.021(1.104～3.701) 0.003** 2.537(1.386～4.646) 0.004** 2.839(1.402～5.747) ↑Male 0.013* 3.056(1.272～7.342) ↑Emergency department 0.013* ↓Traditional Chinese Medicine department 0.001** 11.898(2.584～54.793) ↓Dermatology department 0.007** 6.252(1.659～23.557) ↑Surgery department 0.311 2.261(0.467～10.957) ↓Internal medicine department 0.253 5.442(0.298～99.432) ↓Make-up 0.042* 1.853(1.023～3.356) 0.011* 3.194(1.305～7.817) ↓No body language ＜0.001*** ＜0.001*** 0.003** 0.002** ↓Moderate body language 0.739 0.901(0.490～1.658) 0.898 0.961(0.527～1.754) 0.393 0.770(0.423～1.403) 0.066 0.471(0.211～1.052) ↑Less body language 0.119 0.163(0.017～1.596) 0.088 0.127(0.012～1.363) 0.307 0.402(0.070～2.309) 0.574 0.546(0.066～4.502) ↑More body language ＜0.001*** 0.191(0.091～0.400) ＜0.001*** 0.214(0.104～0.438) ＜0.001*** 0.288(0.148～0.564) ＜0.001*** 0.199(0.086～0.463) ↓Expressiveness 0.055 4.761(0.969～23.404) ↓More facial expression 0.062 4.765(0.922～24.630) ↑Abundant facial expression 0.068 ↑Serious facial expression 0.555 0.748(0.285～1.963) ↓Normal facial expression 0.999 0.000(0.000～Inf) ↑Shooting angle—Side 0.035* ↑Shooting angle—Oblique flank 0.026* 2.914(1.134～7.490) ↓Shooting angle—Front 0.125 2.941(0.743～11.644) ① * P ＜0.05 ** P ＜0.01 *** P ＜0.001 ② ↑ Promoting factors ↓ hindering factors Table 4. The Promoting or hindering effects of parameters in RF models Characteristics Thumb-Up Collection Share Comment production and publication Video Description Length ↑ ↑ ↑ ↑ Video Duration ↑ ↑ ↑ Title Length ↑ ↓ ↑ With Background Music ↓ ↓ With Beauty Filter ↑ ↑ With Sticker ↓ With Name Bar ↓ ↓ Publication from 17:00 to 19:00 ↑ Publication from 8:00 to 11:30 ↓ Publication from 13:30 to 17:00 ↑ With Animation Effects ↓ With Leader Plate ↑ ↑ ↑ Account Name Length= 6 words ↑ ↑ Account Name Length= 5 words ↑ ↑ Account Name Length= 8 words ↓ ↓ No Personal Pronoun in Title ↑ Host characteristics More Body Language ↑ ↑ ↑ Less Body Language ↑ Moderate Body Language ↓ ↓ ↓ ↓ Chief Physician ↓ ↓ Associate Chief Physician ↓ Attending Physician ↑ ↑ ↑ Resident Physician ↑ ↑ Wearing White Gown ↓ Wearing Surgical Gown ↑ ↑ Moderate Facial Expression ↓ ↓ More Facial Expression ↓ ↓ ↓ Specialty - Surgery ↑ ↑ ↑ Specialty - Traditional Chinese Medicine ↓ Make Up ↓ ↓ Gender-Male ↑ Shooting techniques Shooting Location - Department Office ↓ ↓ ↓ Shooting Location - Conference Room ↑ ↑ ↑ Shooting Location - Bedroom ↑ Shooting Scenes - Close Shot ↓ ↓ ↓ Shooting Angle -Front ↓ Shooting Angle - Side ↑ Shooting Angle - Oblique Flank ↑ With Teleprompter ↑ ↑ Shooting Method-Selfie ↓ Shooting Light- F ront light ↑ ↑ ↑ ↑ Promoting factors ↓ hindering factors ； ② Top 5 Factor Highlighting Additional Declarations No competing interests reported. Supplementary Files SupplementaryTable.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4742337","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":339455206,"identity":"1627b9a3-f0f7-486d-9f01-52894c747491","order_by":0,"name":"Nuo Cheng","email":"","orcid":"","institution":"The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Nuo","middleName":"","lastName":"Cheng","suffix":""},{"id":339455207,"identity":"5957aca3-cfb3-40b1-90b6-d4780cb9a4b6","order_by":1,"name":"Xiu-Ling Wang","email":"","orcid":"","institution":"The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiu-Ling","middleName":"","lastName":"Wang","suffix":""},{"id":339455208,"identity":"93c65e80-59a7-4605-a1a3-1313fbaadde4","order_by":2,"name":"Yang Mu","email":"","orcid":"","institution":"Goodwill Information Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Mu","suffix":""},{"id":339455209,"identity":"276a837e-b02e-4841-b063-67c6bb367c8a","order_by":3,"name":"Hui-Jun Li","email":"","orcid":"","institution":"Enduring Medicine Smart Innovation Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Hui-Jun","middleName":"","lastName":"Li","suffix":""},{"id":339455210,"identity":"a73fb50d-3eaf-4a73-99c1-9e611fb1239a","order_by":4,"name":"Yan-Ning Ma","email":"","orcid":"","institution":"The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yan-Ning","middleName":"","lastName":"Ma","suffix":""},{"id":339455211,"identity":"435ca1bb-4fa9-4a27-bcf7-9ddabb6f1640","order_by":5,"name":"Yonghui Yuan","email":"","orcid":"","institution":"Cancer Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yonghui","middleName":"","lastName":"Yuan","suffix":""},{"id":339455212,"identity":"49f3ed87-2036-4d14-a608-bc02cd6f94fd","order_by":6,"name":"Da-Xin Gong","email":"","orcid":"","institution":"The Internet Hospital Branch of the Chinese Research Hospital Association","correspondingAuthor":false,"prefix":"","firstName":"Da-Xin","middleName":"","lastName":"Gong","suffix":""},{"id":339455213,"identity":"98fb182c-ae8c-4221-a839-83f6c81d5f4f","order_by":7,"name":"Shuang Zang","email":"","orcid":"","institution":"China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Zang","suffix":""},{"id":339455214,"identity":"5f7bf5c6-858b-4b9d-bcfc-fe065053cb11","order_by":8,"name":"Guang-Wei Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYHACNhAhh8QmUosx6VoSG4jWIh+R/uzBzx216f3TzhgwfCg7zMA/uwG/FsMbCemGvWeO5864nWPAOOPcYQaJOwcIaJmdcEyCt+1Y7gbpHANm3rbDDAYSCYS0JLZJ/m07lm4A0vKXGC3y0sls0rxtNQlgLYzEaDGQf8YmLdt2wHDG7bSCgz3n0nkkbhCypef4M8m3bXXy/LOTNz74UWYtxz+DkC0HwNRhMAli8+BXD7KlAUzVEVQ4CkbBKBgFIxgAAE4+Qa4Tef95AAAAAElFTkSuQmCC","orcid":"","institution":"The First Hospital of China Medical University","correspondingAuthor":true,"prefix":"","firstName":"Guang-Wei","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-07-15 11:01:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4742337/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4742337/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62756711,"identity":"1396ca0f-6bd1-4951-9d9a-f3fa2c330a13","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":434768,"visible":true,"origin":"","legend":"\u003cp\u003eThe flowchart illustrating the research process for analyzing non-medical factors of medical science popularization short videos.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/ec70c9790afcb77456075caf.png"},{"id":62756710,"identity":"23fd905c-950c-4403-b360-70e8c5890161","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":84848,"visible":true,"origin":"","legend":"\u003cp\u003eThe box plot comparing the AUC values of various models was used to evaluate and select the candidate models based on their performance. AUC: Area under the curve.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/e0d604626a0f21a7f52808e0.png"},{"id":62756717,"identity":"c428b26c-4593-41a1-bda1-bcc2bbf44b2f","added_by":"auto","created_at":"2024-08-19 06:46:03","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":108005,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of Thumb-Up RF Model. \u003cstrong\u003eA\u003c/strong\u003e) The confusion matrix of actual and predicted quantities in low and high groups; \u003cstrong\u003eB\u003c/strong\u003e) ROC curve in validation set; \u003cstrong\u003eC\u003c/strong\u003e) P-R curve in validation set; \u003cstrong\u003eD\u003c/strong\u003e) Rad scores box plot in validation set; \u003cstrong\u003eE\u003c/strong\u003e) Probability distribution map; \u003cstrong\u003eF\u003c/strong\u003e) Calibration plot of the predicted curve in validation set; \u003cstrong\u003eG\u003c/strong\u003e) The decision curves in validation set. \u003cstrong\u003eH\u003c/strong\u003e) The weight analysis for parameters. ROC: Receiver operating characteristic curve.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/b335d180d900292d5b3dbb50.png"},{"id":62756715,"identity":"2cd907e7-5984-492e-9d99-dc06f138e077","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":107024,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of Collection-RF Model. \u003cstrong\u003eA\u003c/strong\u003e) The confusion matrix of actual and predicted quantities in low and high groups; \u003cstrong\u003eB\u003c/strong\u003e) ROC curve in validation set; \u003cstrong\u003eC\u003c/strong\u003e) P-R curve in validation set; \u003cstrong\u003eD\u003c/strong\u003e) Rad scores box plot in validation set; \u003cstrong\u003eE\u003c/strong\u003e) Probability distribution map; \u003cstrong\u003eF\u003c/strong\u003e) Calibration plot of the predicted curve in validation set; \u003cstrong\u003eG\u003c/strong\u003e) The decision curves in validation set. \u003cstrong\u003eH\u003c/strong\u003e) The weight analysis for parameters.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/46b92a7c1e699ae34e87d642.png"},{"id":62756718,"identity":"b43c3f15-2d29-4437-9984-81062f354ec1","added_by":"auto","created_at":"2024-08-19 06:46:03","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":636753,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of Share-RF Model. \u003cstrong\u003eA\u003c/strong\u003e) The confusion matrix of actual and predicted quantities in low and high groups; \u003cstrong\u003eB\u003c/strong\u003e) ROC curve in validation set; \u003cstrong\u003eC\u003c/strong\u003e) P-R curve in validation set; \u003cstrong\u003eD\u003c/strong\u003e) Rad scores box plot in validation set; \u003cstrong\u003eE\u003c/strong\u003e) Probability distribution map; \u003cstrong\u003eF\u003c/strong\u003e) Calibration plot of the predicted curve in validation set; \u003cstrong\u003eG\u003c/strong\u003e) The decision curves in validation set. \u003cstrong\u003eH\u003c/strong\u003e) The weight analysis for parameters.\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/7d1fb738da25fdaa4e67cc59.png"},{"id":62756714,"identity":"18ef1326-29b3-42d7-a55e-6c4564e1e9a5","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":634677,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of Comment-BNB Model. \u003cstrong\u003eA\u003c/strong\u003e) The confusion matrix of actual and predicted quantities in low and high groups; \u003cstrong\u003eB\u003c/strong\u003e) ROC curve in validation set; \u003cstrong\u003eC\u003c/strong\u003e) P-R curve in validation set; \u003cstrong\u003eD\u003c/strong\u003e) Rad scores box plot in validation set; \u003cstrong\u003eE\u003c/strong\u003e) Probability distribution map; \u003cstrong\u003eF\u003c/strong\u003e) Calibration plot of the predicted curve in validation set; \u003cstrong\u003eG\u003c/strong\u003e) The decision curves in validation set. \u003cstrong\u003eH\u003c/strong\u003e) The weight analysis for parameters.\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/4df087b5b3f12852d22c83fb.png"},{"id":62756716,"identity":"1b1d9cde-fa5e-4e94-bda7-f3f2b39652a5","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":628981,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of Comment-RF Model. \u003cstrong\u003eA\u003c/strong\u003e) The confusion matrix of actual and predicted quantities in low and high groups; \u003cstrong\u003eB\u003c/strong\u003e) ROC curve in validation set; \u003cstrong\u003eC\u003c/strong\u003e) P-R curve in validation set; \u003cstrong\u003eD\u003c/strong\u003e) Rad scores box plot in validation set; \u003cstrong\u003eE\u003c/strong\u003e) Probability distribution map; \u003cstrong\u003eF\u003c/strong\u003e) Calibration plot of the predicted curve in validation set; \u003cstrong\u003eG\u003c/strong\u003e) The decision curves in validation set. \u003cstrong\u003eH\u003c/strong\u003e) The weight analysis for parameters.\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/5d0deb8b9daadd0e3b7ef17c.png"},{"id":70893807,"identity":"3b34d59e-0ae4-4a27-915e-b6e88f33d677","added_by":"auto","created_at":"2024-12-09 04:09:33","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4009432,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/c2407a20-cee4-4919-bcae-ec7aeee21ee4.pdf"},{"id":62756712,"identity":"9f7babae-a233-4adb-9346-30794df869e6","added_by":"auto","created_at":"2024-08-19 06:46:02","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":39052,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable.docx","url":"https://assets-eu.researchsquare.com/files/rs-4742337/v1/5268879b319130fa6c51c582.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine learning prediction models for the popularization and dissemination of medical science popularization videos","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003eIn the digital age, medical science popularization videos have become a powerful tool for widely disseminating medical knowledge and information. These videos provide the public with crucial insights into health, disease, and medical technology, thereby promoting public health literacy and behavior [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. TikTok, as one of the most well-known short video platforms all over the world, known for its short and engaging video format. TikTok boasts over 750\u0026nbsp;million daily active users in China[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Compared with traditional information dissemination methods, short videos in TikTok have many advantages, including stronger visibility, attractiveness, interactivity and faster transmission speed, which makes it an emerging medical science popularization videos center[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. The dissemination of these videos helps to narrow the gap between medical professionals and the public, providing short, accessible insights into complex medical topics[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn the dissemination process of medical science popularization videos, it is not only necessary to ensure the reliability and authenticity of the content[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e], but also some non-medical factors can significantly affect the dissemination and attractiveness, such as video production quality, animation, visual aids, and the ability to simplify complex topics contribute to the overall appeal, accessibility of the video and so on[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Compared to the professionalism of medical information, these non-medical factors often play a undeniable role[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Therefore, by analyzing these non-medical factors, it is possible to predict and promote the dissemination intensity and effectiveness of medical science popularization videos. Currently, there are few studies specifically targeting these non-medical factors.\u003c/p\u003e \u003cp\u003eIn recent times, machine learning (ML) models, including but not limited to Decision Tree (DT), Random Forest (RF), have concerned widely because of their outstanding predictive abilities. In contrast to traditional multiple logistic regression (LR) models, ML models operate based on novel logical paradigms, which can more effectively utilize data, and showing enhanced predictive performance on diverse critical fields such as predicting High-risk factors, key feature variables and so on. ML has emerged as a cutting-edge technology for predictive modeling and decision-making[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], providing a promising strategy for constructing influence prediction models for science popularization videos before their release. To this end, this study was designed to search for medical science popularization videos on the TikTok platform, extract non-medical professional feature parameters, conduct a statistical analysis of their distribution characteristics, and subsequently develop and validate ML models for four influence outcome metrics (Thumb-Up, Comment, Share and Collection).\u003c/p\u003e"},{"header":"2 Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study subjects\u003c/h2\u003e \u003cp\u003eWe used \u0026ldquo;medical science popularization\u0026rdquo; as the keyword to search on the TikTok platform (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.TikTok.com/\u003c/span\u003e\u003cspan address=\"https://www.TikTok.com/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) from January to March 2023.\u003c/p\u003e \u003cp\u003eInclusion criteria: 1) The video published by tertiary A hospitals or above; 2) The theme is related to medical science popularization, health education, prevention and treatment, and nursing. Exclusion criteria: The content is repetitive, non-original, commercial, incorrect and involves advertising. A manual review process was employed by two doctors independently. Finally, 286 videos were included, and the video screening process is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Data collection\u003c/h2\u003e \u003cp\u003eTwo doctors extracted information from the video independently. The variables are categorized into three aspects: host characteristics, shooting methods, production and publication \u003cb\u003e(Supplementary Table)\u003c/b\u003e. In addition, we collected the number of \u0026ldquo;Thumb-Up\u0026rdquo;, \u0026ldquo;Comment\u0026rdquo;, \u0026ldquo;Share\u0026rdquo; and \u0026ldquo;Collection\u0026rdquo; for each video, which as indicators for evaluating the effectiveness of video dissemination.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 ML prediction models construction\u003c/h2\u003e \u003cp\u003eA total of 286 samples and 34 variables were included in the construction of the ML predictive models by using the Dr. Wise multimodal research platform (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://keyan.deepwise.com/\u003c/span\u003e\u003cspan address=\"https://keyan.deepwise.com/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e), which is underpinned by Python 3.6 and integrates models from the scikit-learn library (version 0.21.2). Image-related processing was carried out using scikit-image (version 0.16.2)[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. The platform facilitates ML modeling through visualized configuration, encompassing variable setup, partitioning of training and testing datasets, feature engineering (feature cleaning and selection), and model hyperparameter tuning. Once the parameters are configured, the platform invokes Python for model implementation and chart outputs. Based on the distinct distribution characteristics of the data (\u003cb\u003eSupplementary Table\u003c/b\u003e), the median of each outcome was calculated and utilized as cutoff value of binary classification, to construct four types of ML prediction models (Thumb-Up, Collection, Share and Comment). Thirteen classification algorithms were employed to select predictive models, including Decision Tree (DT), K Nearest Neighbors (KNN), Linear Support Vector Classifier (LSVC), Random Forest (RF), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Gradient Boosting, Bernoulli Naive Bayes (NB), Stochastic Gradient Descent (SGD), AdaBoost, XG Boost (XGB), Gaussian Naive Bayes (NB), Logistic Regression (LR).\u003c/p\u003e \u003cp\u003eA 7:3 random split for the entire cohort was repeated 6 times, forming 6 pairs of training and validation sets, for 6 constructions of each algorithm model respectively. For feature dimensionality reduction, two methods were employed: feature correlation analysis and L1 regularization-based feature selection. If the correlation coefficient between features was greater than 0.9, one of the correlated features was retained (feature correlation analysis). L1 regularization-based feature selection involved building a linear model on the training data to obtain a sparse coefficient matrix, whereby features with higher absolute coefficient values were more likely to be retained. The parameter \"C\" controlled the stringency of feature selection; a smaller \"C\" retained fewer features. Following feature selection, the optimal parameters were determined using grid search and the ML models were trained and validated. The preliminary evaluation and comparison of model performance were preformed through averaging the 6 results of area under the curve (AUC), and subsequently a ten-fold cross-validation of the preliminary candidate models was performed for further validation and final confirmation of the best-performing models. Thereafter, the obtained optimal models will be published on the Dr. Wise multimodal research platform at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://keyan.deepwise.com/\u003c/span\u003e\u003cspan address=\"https://keyan.deepwise.com/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (Authorization login required; individuals with prediction and validation needs are encouraged to contact the corresponding author). The platform supports external validation through queuing and allows for predicting the psychological state of individual subjects.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Statistical methods\u003c/h2\u003e \u003cp\u003eThe statistical analyses were conducted with SPSS (version 26.0, SPSS, Chicago, IL, USA) and the Dr. Wise multimodal research platform (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://keyan.deepwise.com/\u003c/span\u003e\u003cspan address=\"https://keyan.deepwise.com/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). Normally distributed data were presented as mean with standard deviation. Non-normally distributed data were expressed as medians (interquartile range [IQR]). Categorical data is represented by the number of examples and rate (%). Multivariate logistic analysis was used to screen the associated factors. A significance level of P\u0026thinsp;\u0026lt;\u0026thinsp;0.05 (two-tailed) was considered to indicate statistically significant differences.\u003c/p\u003e \u003c/div\u003e"},{"header":"3 Results","content":"\u003cp\u003e\u003cstrong\u003e3.1 General information description\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAmong 286 videos, the minimum and maximum numbers of \u0026ldquo;Thumb-Up\u0026rdquo; are 0 and 2.72 million respectively,\u0026nbsp;with an average of 1.46 million \u0026plusmn; 3.61 million. The minimum and maximum numbers of \u0026ldquo;Collection\u0026rdquo; are 1 and 0.14 million respectively, with an average of 0.03 million \u0026plusmn; 0.11 million. The minimum and maximum numbers of \u0026ldquo;Share\u0026rdquo; are 4 and 898 thousand respectively, with an average of 40.57 thousand \u0026plusmn; 86.39 thousand. The minimum and maximum numbers of \u0026ldquo;Comment\u0026rdquo; are 0 and 200 thousand respectively, with an average of 7.70 thousand \u0026plusmn; 20.47 thousand. The four metrics were categorized into high and low groups based on their respective medians, effectively converting continuous variables into binary outcome variables. The median values are 30 thousand (Thumb-Up), 5846 (Collection), 9113 (Share), and 1113.5 (Comment). In terms of host characteristics, the anchors of videos are mainly male, with chief physicians and more specialties in internal medicine. They mostly wear doctor\u0026rsquo;s gown, with no make-up, who are expressive and have more body language. In terms of shooting techniques, videos are often shot from the front of a fixed vertical screen in close range under ambient light, with one person in the majority, often in the department office. In terms of video production and publication, most videos do not have background music, animation effects, beauty effects, and stickers, but have prompts and name bar. The publication time is mostly from 17:00 to 19:00 (\u003cstrong\u003eSupplementary Table\u003c/strong\u003e). There is a positive correlation among the four outcome indicators, and the difference is statistically significant (\u003cstrong\u003eTable 1\u003c/strong\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Comparison of various prediction models\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBased on the results of AUC comparison, we identified 8 candidate models in the preliminary stage, comprising\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e1 for Thumb-Up (\u003cstrong\u003eFigure 2 A\u003c/strong\u003e), 2 for Collection (\u003cstrong\u003eFigure 2 B\u003c/strong\u003e), 2 for Share (\u003cstrong\u003eFigure 2 C\u003c/strong\u003e), 3 for Comment (\u003cstrong\u003eFigure 2 D\u003c/strong\u003e). Subsequently, one model was excluded from each of the last three types, due to substandard calibration curves or decision curves (\u003cstrong\u003eSupplementary Figure 1\u003c/strong\u003e). The five ultimately confirmed best-performing models, predicting the four outcomes, exhibited robust discriminative capabilities, as supported by their respective confusion matrices and ROC curves: \u0026ldquo;Thumb-Up\u0026rdquo; RF Model (AUC=0.7331, \u003cstrong\u003eFigure 3 A\u0026amp;B\u003c/strong\u003e), \u0026ldquo;Collection\u0026rdquo; RF Model (AUC=0.7439, \u003cstrong\u003eFigure 4 A\u0026amp;B\u003c/strong\u003e), \u0026ldquo;Share\u0026rdquo; RF Model (AUC=0.7077, \u003cstrong\u003eFigure 5 A\u0026amp;B\u003c/strong\u003e), \u0026ldquo;Comment\u0026rdquo; RF Model (AUC=0.7960, \u003cstrong\u003eFigure 6 A\u0026amp;B\u003c/strong\u003e), \u0026ldquo;Comment\u0026rdquo; BNB Model (AUC=0.7844, \u003cstrong\u003eFigure 7 A\u0026amp;B\u003c/strong\u003e). Moreover, their Precision-Recall (P-R) curves provide additional validation to the observed robust discriminative ability (the subfigures\u003cstrong\u003e\u0026nbsp;C\u0026nbsp;\u003c/strong\u003eof \u003cstrong\u003eFigure 3 to 7,\u0026nbsp;\u003c/strong\u003erespectively).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAs depicted in \u003cstrong\u003eTable 2,\u003c/strong\u003e the detailed accuracy, sensitivity, specificity, precision, and F1 score for each model highlight their exceptional performance in terms of a more comprehensive presentation, although certain values exhibit an unstable performance, such as the specificity in \u0026ldquo;Share\u0026rdquo; RF Model (0.6163, 95%CI: 0.5601-0.6724). These indications imply that the overall performances of these models are consistent and satisfactory. In terms of calibration, the good overall predictive accuracy of the five models was substantiated by their respective Brier Scores (0.1693, 0.1696,\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e0.0619, 0.1757, 0.1808, all of which are below 0.25). This affirmation was further supported by visual predictive score charts and the calibration curves (the subfigures\u003cstrong\u003e\u0026nbsp;E\u0026amp;F\u0026nbsp;\u003c/strong\u003eof \u003cstrong\u003eFigure 3 to 7,\u0026nbsp;\u003c/strong\u003erespectively). Additionally, the decision curves have also delineated a substantial net benefit within all ML prediction models (the subfigures\u003cstrong\u003e\u0026nbsp;G\u0026nbsp;\u003c/strong\u003eof \u003cstrong\u003eFigure 3 to 7,\u0026nbsp;\u003c/strong\u003erespectively). These indicate that these models have significant value in the prediction and decision-making process, and their predictive outcomes can positively influence decision-making.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.3 Parameter weight analysis results\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAs revealed by the analysis of parameter weights, the video duration, title and description length, shooting location,\u0026nbsp;moderate body Language,\u0026nbsp;emerged as the most five crucial parameters across all five models. Other factors varied in importance across different models (the subfigures\u003cstrong\u003e\u0026nbsp;H\u0026nbsp;\u003c/strong\u003eof \u003cstrong\u003eFigure 3 to 7,\u0026nbsp;\u003c/strong\u003erespectively). The further multivariable logistic regression analysis shows that the video duration, the length of videos description can promote video\u0026rsquo;s dissemination and influence, Less and more body language are factors in promoting all outcomes, while no and\u0026nbsp;moderate\u0026nbsp;body language are hindrance. The factors that hinder public sharing also include make-up. Male, emergency and surgical professionals, abundant and serious facial expressions, side and oblique side shots are factors that promote public comments. Internal medicine and traditional Chinese medicine, make-up, more and normal facial expressions, and front angle shooting are factors that hinder comments (\u003cstrong\u003eTable 3\u003c/strong\u003e). Combining the results of descriptive statistics, ML weight analysis, and multivariable logistic regression analysis, we confirmed the trends of factors that promote or impede Thumb-Up, Collection, Share, and Comment\u0026nbsp;(\u003cstrong\u003eTable 3 and Table 4\u003c/strong\u003e).\u003c/p\u003e"},{"header":"4 Discussion","content":"\u003cp\u003eIn this study, we summarized the current shooting trends of medical science popularization short videos, including host characteristics and commonly used shooting and production techniques, to enhance the understanding of medical scientific information dissemination on this emerging communication platform. Based on these non-medical factors, for the first time, we developed and validated five ML models for predicting the influence of these videos, achieving precise predictions prior to their release. More importantly, these models identified the significance of different influencing factors, providing guidance for the entire video production process. Therefore, this study will help improve public awareness of medical knowledge by elucidating how these factors interact and collectively affect the popularity and dissemination speed of medical content. By enhancing the popularity and dissemination likelihood of these videos, our study is expected to increase the impact of medical science popularization efforts, thereby contributing to the improvement of public health literacy.\u003c/p\u003e \u003cp\u003eIt is necessary and meaningful to study the non-medical factors of medical education video through the TikTok. TikTok has become a vital video platform for sharing fascinating scientific knowledge[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. More and more health care professionals use the TikTok to convey important health information to the public, and more research focuses on the analysis of medical care professional video content and form on TikTok[\u003cspan additionalcitationids=\"CR15\" citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e–\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Du et al[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] explored the content and quality of videos on the TikTok and Bilibili platforms, and analyzed the relationship with the number of views, comments, shares, and favorites. Rudisill et al[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] and wang et al[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] evaluated the reliability and educational quality of videos and found that longer video durations predicted higher scores, the former show that there is no independent correlation between the uploaded source or content and quality score, while the latter show that academic and clinical sources can lead to the higher video quality. A study noted the influence of non-medical factors such as video style, original music by analyzing the likes, comments, and reposts of the top 100 most popular micro-videos[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Li et al[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] investigate how the video attributes (video format, type and content) are related to quantitative indicators of user engagement (numbers of views, likes, comments and shares). Although these studies suggest that non-medical factors may be key to attracting the public to watch videos, there has few studies focused exclusively on these non-medical factors. Therefore, this study controlled for consistency in professionalism and quality to observe the impact of non-medical factors on the four influence indicators. The results further directly demonstrate the critical role of non-medical factors. The significant differences in views, likes, shares, and collections between videos caused by non-medical factors suggest that these factors may have a more decisive influence than the video's professionalism and quality. This can be primarily explained by the fact that the audience often lacks expertise in medical knowledge, making them likely to overlook medical professionalism and instead rely on non-medical factors to judge whether a science popularization video is worth watching and sharing.\u003c/p\u003e \u003cp\u003eFrom a methodological perspective, analyzing video health communication is currently widely based on content analysis methods[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Some studies also use multivariate linear analysis based on traditional statistics to explore the factors related to video quality and associated factors[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. However, referring to the development of medical big data mining research, these methods have significant limitations in exploring the complex nonlinear relationships commonly present among data[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. In recent times, ML has emerged as a cutting-edge technology for predictive modeling and decision-making, substantially enhancing the precision of outcome predictions[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Additionally, ML model can distinguish the importance of different variables, and avoid the one-sided and subjective observation of a single indicator alone[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Therefore, it has been widely applied in the development of predictive models across various research domains[\u003cspan additionalcitationids=\"CR28\" citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e–\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. In the field of video science popularization, ML is commonly used to analyze and evaluate public willingness[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e] and emotional tendencies[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e, \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e], as well as to analyze video quality[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. For example, by using ML to identify, retrieve, and qualify medical related and understandable YouTube videos, domain experts can then review and recommend these videos for dissemination and public education[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. Usman et al[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e] proposed that ML models can effectively predict customer satisfaction from healthcare datasets. Alghamdi et al[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e] used ML models for fake news detection, which demonstrate good predictive performance. In this study, we adopted the application models of ML from the field of disease prediction to explore the development of influence prediction models for medical science popularization videos, by comparing the performance of 13 commonly used ML algorithms. Finally, the FR algorithm was confirmed as the best-performing model across the four outcome indicators, while the BNB algorithm showed consistent and satisfactory performance specifically for the “Comment” outcome. These findings regarding ML algorithms are consistent with patterns reported in numerous studies[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. Our results not only indicate that non-medical factors can predict the influence of science popularization videos, but also demonstrate that ML algorithms can significantly enhance this predictive ability. Moreover, we found that nonlinear algorithms significantly outperform traditional linear algorithms (e.g., LR), further confirming the existence of complex data relationships between non-medical factors and outcomes.\u003c/p\u003e \u003cp\u003eWe found that in terms of host characteristics, the chief physician and associate chief physician assume educational responsibilities, but the attending physician and resident physician are more popular among people. Although the chief physician and associate chief physician have more experience and expertise, lower-level physicians may be more humorous, their shooting methods or content being more vivid and interesting. Studies have shown that humor can significantly enhance user immersion and entertainment, especially when combined with medical information, thereby enhancing user acceptance[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. People are not very interested in the image of wearing a white coat, but they are more interested in medical personnel wearing surgical gowns. At the same time, research results show that people are more interested in and pay more attention to science popularization videos of surgical professionals. Moderate Body Language is not beneficial, more body language demonstrates good effects, which can demonstrate the professionalism and affinity of host. Surprisingly, make-up does not attract attention. Although people have requirements for beauty[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e], this requirement seems to not applicable to medical science popularization.\u003c/p\u003e \u003cp\u003eIn terms of Shooting techniques, the shooting location, scene, and angle have a higher weight. The video shooting in the department office is not good, while in the conference room is better. It may be because the environment of the department office is relatively noisy, the conference room is relatively quiet, resulting in better video shooting and presentation effects[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. The dissemination effect of close-up shooting is better, and the shooting angles of the side and oblique sides are also better than those of frontal shooting. The video shoted in these methods are natural and clear, and therefore more popular among people. In terms of video production and publication, the length of video description, duration, and length of questions can all affect the dissemination and engagement. Videos on TikTok with the shortest duration received the most numbers of “likes\", “comments\", and “shares\"[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]. Zhu et al[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] found that the presentation method of micro-video is more popular. The duration of the video should not be too long, and the title and video descriptions content should be concise, clear, and easy to understand[\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. Proper use of beauty filters is beneficial, but background music should be used with caution. Sometimes background music may give people a scripted feeling or mask some of the sound[\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]. Medical videos should ensure their rigor and seriousness, and should be convincing and serious. Therefore, beauty filters should be used moderately, and appropriate background music should be chosen. The popularity and dissemination effect of videos released from 13:30 to 19:00 are better, videos released in the afternoon are more likely to be shared with others, and videos released later are more likely to receive likes. Most people are working or busy during the day, users are more likely to invest more effort for the time-consuming activity of watching the video in the evening.[\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eHowever, this study has certain limitations. Firstly, the videos screened in this study are in Chinese. Consequently, the findings derived from this study may not be readily applicable to videos in other languages found on TikTok. Secondly, we searched from January to March 2023 and obtained 286 samples only, which is relatively small, we will conduct larger sample studies in the future.\u003c/p\u003e "},{"header":"Conclusions","content":"\u003cp\u003eML models have shown superior performance in predicting non-medical factors that affect the dissemination of medical science popularization videos, and can better demonstrate the nonlinear relationships between factors. In addition to the reliability and authenticity of medical science popularization videos, the following points should also be noted. The duration of the video should be short, and the title and video description content should be concise and clear. The shooting location should be in the conference room. The physicians in the video should not use excessive body language or excessive make-up, but can use beauty filters in moderation. The video content should be vivid, interesting, and easier to understand. Based on our research findings, we hope to provide reference for the production and filming of short videos in the future, so that short videos can be better disseminated and accepted by the public, in order to promote health education, and enhance public awareness and ability in health care.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eML= machine learning\u003c/p\u003e\n\u003cp\u003eAUC= area under the curve\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eDT= Decision Tree\u003c/p\u003e\n\u003cp\u003eRF= Random Forest\u003c/p\u003e\n\u003cp\u003eLR= logistic regression\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eThe Conflict of Interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone declared.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e(1) concept and design：Nuo Cheng, Xiu-Ling Wang, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang\u003c/p\u003e\n\u003cp\u003e（2）acquisition of data：Nuo Cheng, Hui-Jun Li, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang\u003c/p\u003e\n\u003cp\u003e（3）analysis of data：Xiu-Ling Wang, Yang Mu, Hui-Jun Li, Yan-Ning Ma, Yonghui Yuan, Guang-Wei Zhang\u003c/p\u003e\n\u003cp\u003e（4）preparation of manuscript：Nuo Cheng, Xiu-Ling Wang completed the first draft, and Nuo Cheng, Da-Xin Gong, Shuang Zang, Guang-Wei Zhang revised it.\u003c/p\u003e\n\u003cp\u003eAll authors read and approved the final manuscript.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by the National Key Research and Development Program of China [No. 2020YFC2006401 \u0026amp; 2020YFC2006406], Science and Technology Projects in Liaoning Province (2023JH2/20200056), Project of Applied Basic Research Program of Liaoning province (2023JH26/10300016), and National College Students\u0026apos; innovation and entrepreneurship training program (No. 202110159005). Technical assistance provided by Hangzhou Deepwise \u0026amp; League of PHD Technology Co., Ltd is gratefully acknowledged.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAppendix A. Supplementary \u0026nbsp;material\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData is provided within the manuscript or supplementary information files.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eSeifert, L.B., et al., \u003cem\u003e#OMFSurgery: analyzing the use of social media applications in oral and maxillofacial surgery resident training.\u003c/em\u003e BMC Oral Health, 2023. \u003cstrong\u003e23\u003c/strong\u003e(1): p. 212.\u003c/li\u003e\n\u003cli\u003eTian, K., et al., \u003cem\u003eThe impact of perceived value and affection on Chinese residents\u0026apos; continuous use intention of mobile health science information: An empirical study.\u003c/em\u003e Front Public Health, 2023. \u003cstrong\u003e11\u003c/strong\u003e: p. 1034231.\u003c/li\u003e\n\u003cli\u003eLiu, H., et al., \u003cem\u003eAssessment of the reliability and quality of breast cancer related videos on TikTok and Bilibili: cross-sectional study in China.\u003c/em\u003e Front Public Health, 2023. \u003cstrong\u003e11\u003c/strong\u003e: p. 1296386.\u003c/li\u003e\n\u003cli\u003eLiu, K., \u003cem\u003eResearch on the core competitiveness of short video industry in the context of big data\u0026mdash;a case study of tiktok of bytedance company.\u003c/em\u003e American Journal of Industrial and Business Management, 2022. \u003cstrong\u003e12\u003c/strong\u003e(4): p. 699-730.\u003c/li\u003e\n\u003cli\u003eThimbleby, H., \u003cem\u003eTechnology and the future of healthcare.\u003c/em\u003e J Public Health Res, 2013. \u003cstrong\u003e2\u003c/strong\u003e(3): p. e28.\u003c/li\u003e\n\u003cli\u003eO\u0026apos;Sullivan, N.J., et al., \u003cem\u003eThe unintentional spread of misinformation on \u0026apos;TikTok\u0026apos;; A paediatric urological perspective.\u003c/em\u003e J Pediatr Urol, 2022. \u003cstrong\u003e18\u003c/strong\u003e(3): p. 371-375.\u003c/li\u003e\n\u003cli\u003eZhang, J., et al., \u003cem\u003ePopular science and education of cosmetic surgery in China: Quality and reliability evaluation of Douyin short videos.\u003c/em\u003e Health Expect, 2023. \u003cstrong\u003e26\u003c/strong\u003e(3): p. 1221-1226.\u003c/li\u003e\n\u003cli\u003eMontag, C., H. Yang, and J.D. Elhai, \u003cem\u003eOn the Psychology of TikTok Use: A First Glimpse From Empirical Findings.\u003c/em\u003e Front Public Health, 2021. \u003cstrong\u003e9\u003c/strong\u003e: p. 641673.\u003c/li\u003e\n\u003cli\u003eBasch, C.H., et al., \u003cem\u003eHow TikTok Is Being Used to Help Individuals Cope With Breast Cancer: Cross-sectional Content Analysis.\u003c/em\u003e JMIR Cancer, 2022. \u003cstrong\u003e8\u003c/strong\u003e(4): p. e42245.\u003c/li\u003e\n\u003cli\u003eLiang, Q., et al., \u003cem\u003ePrediction of successful weaning from renal replacement therapy in critically ill patients based on machine learning.\u003c/em\u003e Ren Fail, 2024. \u003cstrong\u003e46\u003c/strong\u003e(1): p. 2319329.\u003c/li\u003e\n\u003cli\u003eZhang, Y.B., et al., \u003cem\u003eDevelopment of a machine learning-based model for predicting risk of early postoperative recurrence of hepatocellular carcinoma.\u003c/em\u003e World J Gastroenterol, 2023. \u003cstrong\u003e29\u003c/strong\u003e(43): p. 5804-5817.\u003c/li\u003e\n\u003cli\u003eXu, A., et al., \u003cem\u003eDevelopment and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma.\u003c/em\u003e BMC Cancer, 2022. \u003cstrong\u003e22\u003c/strong\u003e(1): p. 872.\u003c/li\u003e\n\u003cli\u003eComp, G., S. Dyer, and M. Gottlieb, \u003cem\u003eIs TikTok The Next Social Media Frontier for Medicine?\u003c/em\u003e AEM Educ Train, 2021. \u003cstrong\u003e5\u003c/strong\u003e(3).\u003c/li\u003e\n\u003cli\u003eBasch, C.H., et al., \u003cem\u003eDeconstructing TikTok Videos on Mental Health: Cross-sectional, Descriptive Content Analysis.\u003c/em\u003e JMIR Form Res, 2022. \u003cstrong\u003e6\u003c/strong\u003e(5): p. e38340.\u003c/li\u003e\n\u003cli\u003eChasca, W., et al., \u003cem\u003eTikTok and #OccupationalTherapy: Cross-sectional Study.\u003c/em\u003e JMIR Form Res, 2023. \u003cstrong\u003e7\u003c/strong\u003e: p. e45554.\u003c/li\u003e\n\u003cli\u003eZhu, C., et al., \u003cem\u003eHow Health Communication via Tik Tok Makes a Difference: A Content Analysis of Tik Tok Accounts Run by Chinese Provincial Health Committees.\u003c/em\u003e Int J Environ Res Public Health, 2019. \u003cstrong\u003e17\u003c/strong\u003e(1).\u003c/li\u003e\n\u003cli\u003eDu, R.C., et al., \u003cem\u003eTikTok and Bilibili as sources of information on Helicobacter pylori in China: A content and quality analysis.\u003c/em\u003e Helicobacter, 2023. \u003cstrong\u003e28\u003c/strong\u003e(5): p. e13007.\u003c/li\u003e\n\u003cli\u003eRudisill, S.S., et al., \u003cem\u003eYouTube as a source of information on pediatric scoliosis: a reliability and educational quality analysis.\u003c/em\u003e Spine Deform, 2023. \u003cstrong\u003e11\u003c/strong\u003e(1): p. 3-9.\u003c/li\u003e\n\u003cli\u003eWang, H., et al., \u003cem\u003eYouTube online videos as a source for patient education of cervical spondylosis-a reliability and quality analysis.\u003c/em\u003e BMC Public Health, 2023. \u003cstrong\u003e23\u003c/strong\u003e(1): p. 1831.\u003c/li\u003e\n\u003cli\u003eLi, Y., et al., \u003cem\u003eCommunicating COVID-19 information on TikTok: a content analysis of TikTok videos from official accounts featured in the COVID-19 information hub.\u003c/em\u003e Health Educ Res, 2021. \u003cstrong\u003e36\u003c/strong\u003e(3): p. 261-271.\u003c/li\u003e\n\u003cli\u003eFrohlich, D.O. and A. Zmyslinski-Seelig, \u003cem\u003eThe presence of social support messages on YouTube videos about inflammatory bowel disease and ostomies.\u003c/em\u003e Health Commun, 2012. \u003cstrong\u003e27\u003c/strong\u003e(5): p. 421-8.\u003c/li\u003e\n\u003cli\u003eKwak, D., et al., \u003cem\u003eQuality and reliability evaluation of online videos on carpal tunnel syndrome: a YouTube video-based study.\u003c/em\u003e BMJ Open, 2022. \u003cstrong\u003e12\u003c/strong\u003e(4): p. e059239.\u003c/li\u003e\n\u003cli\u003eBaker, J.D., et al., \u003cem\u003eAssessing the Quality and Credibility of Publicly Available Videos on Cervical Fusion: Is YouTube a Reliable Educational Tool?\u003c/em\u003e Int J Spine Surg, 2021. \u003cstrong\u003e15\u003c/strong\u003e(4): p. 669-675.\u003c/li\u003e\n\u003cli\u003eByeon, H., \u003cem\u003eScreening dementia and predicting high dementia risk groups using machine learning.\u003c/em\u003e World J Psychiatry, 2022. \u003cstrong\u003e12\u003c/strong\u003e(2): p. 204-211.\u003c/li\u003e\n\u003cli\u003eWaljee, A.K. and P.D. Higgins, \u003cem\u003eMachine learning in medicine: a primer for physicians.\u003c/em\u003e Am J Gastroenterol, 2010. \u003cstrong\u003e105\u003c/strong\u003e(6): p. 1224-6.\u003c/li\u003e\n\u003cli\u003eHuang, K., et al., \u003cem\u003eRandom Forest Model for Labor Induction in Pregnant Women With Hypertensive Disorders Using a Cervical Double Balloon.\u003c/em\u003e Altern Ther Health Med, 2023. \u003cstrong\u003e29\u003c/strong\u003e(1): p. 44-51.\u003c/li\u003e\n\u003cli\u003eXiang, K., et al., \u003cem\u003eTM-Score predicts immunotherapy efficacy and improves the performance of the machine learning prognostic model in gastric cancer.\u003c/em\u003e Int Immunopharmacol, 2024. \u003cstrong\u003e134\u003c/strong\u003e: p. 112224.\u003c/li\u003e\n\u003cli\u003eCai, Y., et al., \u003cem\u003eArtificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review.\u003c/em\u003e BMC Med, 2024. \u003cstrong\u003e22\u003c/strong\u003e(1): p. 56.\u003c/li\u003e\n\u003cli\u003ePencina, M.J., B.A. Goldstein, and R.B. D\u0026apos;Agostino, \u003cem\u003ePrediction Models - Development, Evaluation, and Clinical Application.\u003c/em\u003e N Engl J Med, 2020. \u003cstrong\u003e382\u003c/strong\u003e(17): p. 1583-1586.\u003c/li\u003e\n\u003cli\u003eKinugasa, Y., et al., \u003cem\u003eFactors affecting the willingness of nursing care staffs for cooperation with heart failure care and the role of internet video education.\u003c/em\u003e J Gen Fam Med, 2024. \u003cstrong\u003e25\u003c/strong\u003e(1): p. 19-27.\u003c/li\u003e\n\u003cli\u003eAsghari, M., et al., \u003cem\u003eClassifying Comments on Social Media Related to Living Kidney Donation: Machine Learning Training and Validation Study.\u003c/em\u003e JMIR Med Inform, 2022. \u003cstrong\u003e10\u003c/strong\u003e(11): p. e37884.\u003c/li\u003e\n\u003cli\u003eZheng, C., et al., \u003cem\u003ePublic Opinions and Concerns Regarding the Canadian Prime Minister\u0026apos;s Daily COVID-19 Briefing: Longitudinal Study of YouTube Comments Using Machine Learning Techniques.\u003c/em\u003e J Med Internet Res, 2021. \u003cstrong\u003e23\u003c/strong\u003e(2): p. e23957.\u003c/li\u003e\n\u003cli\u003eRodriguez-Rodriguez, A.M., et al., \u003cem\u003eQuality Analysis of YouTube Videos Presenting Pelvic Floor Exercises after Prostatectomy Surgery.\u003c/em\u003e J Pers Med, 2021. \u003cstrong\u003e11\u003c/strong\u003e(9).\u003c/li\u003e\n\u003cli\u003eRodriguez Rodriguez, A.M., et al., \u003cem\u003eQuality Analysis of YouTube Videos Presenting Shoulder Exercises after Breast Cancer Surgery.\u003c/em\u003e Breast Care (Basel), 2022. \u003cstrong\u003e17\u003c/strong\u003e(2): p. 188-198.\u003c/li\u003e\n\u003cli\u003eGuo, Y., et al., \u003cem\u003eYouTube Videos for Public Health Literacy? A Machine Learning Pipeline to Curate Covid-19 Videos.\u003c/em\u003e Stud Health Technol Inform, 2024. \u003cstrong\u003e310\u003c/strong\u003e: p. 760-764.\u003c/li\u003e\n\u003cli\u003eUsman, M., et al., \u003cem\u003eAnalyzing patients satisfaction level for medical services using twitter data.\u003c/em\u003e PeerJ Comput Sci, 2024. \u003cstrong\u003e10\u003c/strong\u003e: p. e1697.\u003c/li\u003e\n\u003cli\u003eAlghamdi, J., Y. Lin, and S. Luo, \u003cem\u003eTowards COVID-19 fake news detection using transformer-based models.\u003c/em\u003e Knowl Based Syst, 2023. \u003cstrong\u003e274\u003c/strong\u003e: p. 110642.\u003c/li\u003e\n\u003cli\u003eKim, D.W., et al., \u003cem\u003eMachine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report.\u003c/em\u003e Bone, 2018. \u003cstrong\u003e116\u003c/strong\u003e: p. 207-214.\u003c/li\u003e\n\u003cli\u003eMcBriar, J.D., et al., \u003cem\u003e#Neurosurgery: A Cross-Sectional Analysis of Neurosurgical Content on TikTok.\u003c/em\u003e World Neurosurg X, 2023. \u003cstrong\u003e17\u003c/strong\u003e: p. 100137.\u003c/li\u003e\n\u003cli\u003eXu, Y., J. Wang, and M. Ma, \u003cem\u003eAdapting to Lockdown: Exploring Stress Coping Strategies on Short Video Social Media During the COVID-19 Pandemic.\u003c/em\u003e Psychol Res Behav Manag, 2023. \u003cstrong\u003e16\u003c/strong\u003e: p. 5273-5287.\u003c/li\u003e\n\u003cli\u003eKou, L., et al., \u003cem\u003eObservation for clinical effect of acupuncture combined with conventional therapy in the treatment of acne vulgaris.\u003c/em\u003e Medicine (Baltimore), 2020. \u003cstrong\u003e99\u003c/strong\u003e(18): p. e19764.\u003c/li\u003e\n\u003cli\u003eMolavynejad, S., M. Miladinia, and M. Jahangiri, \u003cem\u003eA randomized trial of comparing video telecare education vs. in-person education on dietary regimen compliance in patients with type 2 diabetes mellitus: a support for clinical telehealth Providers.\u003c/em\u003e BMC Endocr Disord, 2022. \u003cstrong\u003e22\u003c/strong\u003e(1): p. 116.\u003c/li\u003e\n\u003cli\u003eCai, Q.Y., et al., \u003cem\u003eQuality assessment of videos on social media platforms related to gestational diabetes mellitus in China: A cross-section study.\u003c/em\u003e Heliyon, 2024. \u003cstrong\u003e10\u003c/strong\u003e(7): p. e29020.\u003c/li\u003e\n\u003cli\u003eRooney, M.K., et al., \u003cem\u003eReadability of Patient Education Materials From High-Impact Medical Journals: A 20-Year Analysis.\u003c/em\u003e J Patient Exp, 2021. \u003cstrong\u003e8\u003c/strong\u003e: p. 2374373521998847.\u003c/li\u003e\n\u003cli\u003eBarratt, E.L., C. Spence, and N.J. Davis, \u003cem\u003eSensory determinants of the autonomous sensory meridian response (ASMR): understanding the triggers.\u003c/em\u003e PeerJ, 2017. \u003cstrong\u003e5\u003c/strong\u003e: p. e3846.\u003c/li\u003e\n\u003cli\u003eConnelly, Y., et al., \u003cem\u003eImplementation of a Personalized Digital App for Pediatric Preanesthesia Evaluation and Education: Ongoing Usability Analysis and Dynamic Improvement Scheme.\u003c/em\u003e JMIR Form Res, 2022. \u003cstrong\u003e6\u003c/strong\u003e(5): p. e34129.\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1. \u0026nbsp;The correlation among the four outcome indicators (N=286)\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"624\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"36.32%\" colspan=\"2\" valign=\"bottom\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.72%\" valign=\"bottom\"\u003e\n \u003cp\u003e\u003cstrong\u003eThumb-Up\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.32%\" valign=\"bottom\"\u003e\n \u003cp\u003e\u003cstrong\u003eCollection\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.32%\" valign=\"bottom\"\u003e\n \u003cp\u003e\u003cstrong\u003eshare\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.32%\" valign=\"bottom\"\u003e\n \u003cp\u003e\u003cstrong\u003ecomment\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.738019169329073%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eThumb-Up\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"22.68370607028754%\" valign=\"top\"\u003e\n \u003cp\u003ePearson correlation (r)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.696485623003195%\" valign=\"top\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"26.296296296296298%\" valign=\"top\"\u003e\n \u003cp\u003eSig.（two-tailed）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.037037037037038%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.738019169329073%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eCollection\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"22.68370607028754%\" valign=\"top\"\u003e\n \u003cp\u003ePearson correlation (r)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.696485623003195%\" valign=\"top\"\u003e\n \u003cp\u003e0.350\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"26.296296296296298%\" valign=\"top\"\u003e\n \u003cp\u003eSig.（two-tailed）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.037037037037038%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.738019169329073%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eshare\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"22.68370607028754%\" valign=\"top\"\u003e\n \u003cp\u003ePearson correlation (r)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.696485623003195%\" valign=\"top\"\u003e\n \u003cp\u003e0.308\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e0.495\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"26.296296296296298%\" valign=\"top\"\u003e\n \u003cp\u003eSig.（two-tailed）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.037037037037038%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.738019169329073%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ecomment\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"22.68370607028754%\" valign=\"top\"\u003e\n \u003cp\u003ePearson correlation (r)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.696485623003195%\" valign=\"top\"\u003e\n \u003cp\u003e0.728\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e0.555\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e0.478\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.293929712460063%\" valign=\"top\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"26.296296296296298%\" valign=\"top\"\u003e\n \u003cp\u003eSig.（two-tailed）\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.037037037037038%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e＜0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.88888888888889%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"100%\" colspan=\"6\" valign=\"top\"\u003e\n \u003cp\u003e**\u003cem\u003eP\u003c/em\u003e＜0.01\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2. Analysis of predictive performance for five prediction models\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"652\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\" rowspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrediction Models\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"72.54601226993866%\" colspan=\"5\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePerformance (95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"20.084566596194502%\"\u003e\n \u003cp\u003eAccuracy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"19.873150105708245%\"\u003e\n \u003cp\u003eSensitivity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.084566596194502%\"\u003e\n \u003cp\u003eSpecificity\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"19.873150105708245%\"\u003e\n \u003cp\u003ePrecision\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.084566596194502%\"\u003e\n \u003cp\u003eF1 score\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ldquo;Thumb-Up\u0026rdquo; RF Model\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6531\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6229-0.6833)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6241\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6023-0.6458)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6822\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.63-0.7344)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6649\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6251-0.7046)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6432\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6176-0.6687)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ldquo;Collection\u0026rdquo; RF Model\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6802\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6446-0.7159)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6938\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6476-0.74)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6119-0.7214)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.677\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6394-0.7147)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6842\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6491-0.7193)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ldquo;Share\u0026rdquo; RF Model\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6492\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6202-0.6783)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6822\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6437-0.7206)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6163\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.5601-0.6724)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6419\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6083-0.6755)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6604\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6341-0.6866)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ldquo;Comment\u0026rdquo; RF model\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.7171\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.7019-0.7323)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.7442\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.7018-0.7866)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6899\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6553-0.7246)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.7069\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6893-0.7245)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.7239\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.704-0.7438)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"27.45398773006135%\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ldquo;\u003c/strong\u003e\u003cstrong\u003eComment\u0026rdquo; BNB model\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.7093\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.683-0.7356)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.6706\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.6488-0.6923)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.7481\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;(0.705-0.7912)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.417177914110429%\"\u003e\n \u003cp\u003e0.7286\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6927-0.7644)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.570552147239264%\"\u003e\n \u003cp\u003e0.6979\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0.6738-0.7219)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3. \u0026nbsp;parameters in the multivariable logistic regression model\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"662\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"12.971342383107089%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eCharacteristics\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"21.417797888386122%\" colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eThumb-Up\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"21.417797888386122%\" colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eCollection\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"21.417797888386122%\" colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eShare\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"22.77526395173454%\" colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eComment\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"8.173913043478262%\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.347826086956523%\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"8.173913043478262%\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.347826086956523%\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"8.173913043478262%\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"16.52173913043478%\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"8.173913043478262%\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.08695652173913%\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026uarr;Video duration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.001**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e1.009(1.003～1.014)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.001**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e1.008(1.003～1.013)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.003**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e1.007(1.002～1.012)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.003**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e1.009(1.003～1.015)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026uarr;Video description length\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.006**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e1.046(1.013～1.080)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.004**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e1.058(1.018～1.100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026darr;With prompt\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.023*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e2.021(1.104～3.701)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.003**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e2.537(1.386～4.646)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.004**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e2.839(1.402～5.747)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026uarr;Male\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.013*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e3.056(1.272～7.342)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Emergency\u0026nbsp;department\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.013*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"20.12102874432678%\" colspan=\"2\"\u003e\n \u003cp\u003e\u0026darr;Traditional Chinese Medicine\u0026nbsp;department\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.001**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e11.898(2.584～54.793)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026darr;Dermatology\u0026nbsp;department\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.007**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e6.252(1.659～23.557)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Surgery\u0026nbsp;department\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.311\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e2.261(0.467～10.957)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026darr;Internal medicine\u0026nbsp;department\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.253\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e5.442(0.298～99.432)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026darr;Make-up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.042*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e1.853(1.023～3.356)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.011*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e3.194(1.305～7.817)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026darr;No body language\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.003**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.002**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026darr;Moderate body language\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.739\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.901(0.490～1.658)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.898\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.961(0.527～1.754)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.393\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e0.770(0.423～1.403)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.066\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e0.471(0.211～1.052)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026uarr;Less body language\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.163(0.017～1.596)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.088\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.127(0.012～1.363)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.307\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e0.402(0.070～2.309)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.574\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e0.546(0.066～4.502)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026uarr;More\u0026nbsp;body language\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.191(0.091～0.400)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e0.214(0.104～0.438)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e0.288(0.148～0.564)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e＜0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e0.199(0.086～0.463)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026darr;Expressiveness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.055\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e4.761(0.969～23.404)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026darr;More facial expression\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.062\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e4.765(0.922～24.630)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Abundant facial expression\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.068\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Serious facial expression\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.555\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e0.748(0.285～1.963)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026darr;Normal facial expression\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.999\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e0.000(0.000～Inf)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Shooting angle\u0026mdash;Side\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.035*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026uarr;Shooting angle\u0026mdash;Oblique flank\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.026*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e2.914(1.134～7.490)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"13.010590015128592%\"\u003e\n \u003cp\u003e\u0026darr;Shooting angle\u0026mdash;Front\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.22087745839637%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"14.372163388804841%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"7.110438729198185%\" valign=\"top\"\u003e\n \u003cp\u003e0.125\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.733736762481088%\" valign=\"top\"\u003e\n \u003cp\u003e2.941(0.743～11.644)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e①\u0026nbsp;*\u003cem\u003eP\u003c/em\u003e＜0.05 \u0026nbsp; \u0026nbsp;**\u003cem\u003eP\u003c/em\u003e＜0.01 \u0026nbsp; \u0026nbsp;***\u003cem\u003eP\u003c/em\u003e＜0.001\u003c/p\u003e\n\u003cp\u003e② \u0026uarr; Promoting factors \u0026nbsp; \u0026darr; hindering factors\u003c/p\u003e\n\u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eTable 4. \u0026nbsp;The\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003ePromoting\u003c/span\u003e\u003c/strong\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;or hindering effects of parameters in RF models\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable style=\"width:494.1pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;border-top: 1pt solid windowtext;border-left: none;border-bottom: 1pt solid windowtext;border-right: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;margin-top:0in;margin-right:3.0pt;margin-bottom:.0001pt;margin-left:3.0pt;text-indent:12.05pt;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eCharacteristics\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:69.1pt;border-top:solid windowtext 1.0pt;border-left:none;border-bottom:solid windowtext 1.0pt;border-right:none;padding:0in 5.4pt 0in 5.4pt;height:14.2pt;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;text-indent:12.05pt;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eThumb-Up\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:69.1pt;border-top:solid windowtext 1.0pt;border-left:none;border-bottom:solid windowtext 1.0pt;border-right:none;padding:0in 5.4pt 0in 5.4pt;height:14.2pt;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;text-indent:12.05pt;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eCollection\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:69.1pt;border-top:solid windowtext 1.0pt;border-left:none;border-bottom:solid windowtext 1.0pt;border-right:none;padding:0in 5.4pt 0in 5.4pt;height:14.2pt;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;text-indent:12.05pt;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eShare\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:69.15pt;border-top:solid windowtext 1.0pt;border-left:none;border-bottom:solid windowtext 1.0pt;border-right:none;padding:0in 5.4pt 0in 5.4pt;height:14.2pt;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;text-indent:12.05pt;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eComment\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;border: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-family: \"Times New Roman\",serif;color:black;'\u003eproduction and publication\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;border: none;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eVideo Description Length\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eVideo Duration\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eTitle Length\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Background Music\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Beauty Filter\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Sticker\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Name Bar\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003ePublication from 17:00 to 19:00\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003ePublication from 8:00 to 11:30\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003ePublication from 13:30 to 17:00\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Animation Effects\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Leader Plate\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAccount Name Length= 6 words\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAccount Name Length= 5 words\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAccount Name Length= 8 words\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eNo Personal Pronoun in Title\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:217.65pt;padding:0in 5.4pt 0in 5.4pt;height:14.2pt;\"\u003e\n \u003cp style='margin:0in;text-align:left;font-size:14px;font-family:\"Calibri\",sans-serif;margin-top:2.0pt;margin-right:5.0pt;margin-bottom:7.8pt;margin-left:0in;'\u003e\u003cstrong\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eHost characteristics\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eMore Body Language\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eLess Body Language\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eModerate Body Language\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eChief Physician\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAssociate Chief Physician\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eAttending Physician\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eResident Physician\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWearing White Gown\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWearing Surgical Gown\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eModerate Facial Expression\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eMore Facial Expression\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eSpecialty - Surgery\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eSpecialty - Traditional Chinese Medicine\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eMake Up\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eGender-Male\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-family: \"Times New Roman\",serif;color:black;'\u003eShooting techniques\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Location - Department Office\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Location - Conference Room\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Location - Bedroom\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Scenes - Close Shot\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;background:yellow;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Angle -Front\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Angle - Side\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Angle - Oblique Flank\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eWith Teleprompter\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Method-Selfie\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026darr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217.65pt;border-top: none;border-right: none;border-left: none;border-image: initial;border-bottom: 1pt solid windowtext;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:justify;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003eShooting Light-\u003cspan style=\"color:black;\"\u003eF\u003c/span\u003e\u003c/span\u003e\u003cspan style='font-family:\"Times New Roman\",serif;color:black;'\u003eront light\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border-top: none;border-right: none;border-left: none;border-image: initial;border-bottom: 1pt solid windowtext;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border-top: none;border-right: none;border-left: none;border-image: initial;border-bottom: 1pt solid windowtext;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.1pt;border-top: none;border-right: none;border-left: none;border-image: initial;border-bottom: 1pt solid windowtext;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69.15pt;border-top: none;border-right: none;border-left: none;border-image: initial;border-bottom: 1pt solid windowtext;padding: 0in 5.4pt;height: 14.2pt;vertical-align: top;\"\u003e\n \u003cp style='margin:0in;text-align:center;font-size:14px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026uarr;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cspan style='font-size:12px;font-family:\"Times New Roman\",serif;'\u003e\u0026uarr; Promoting factors \u0026nbsp; \u0026darr; hindering factors\u003c/span\u003e\u003cspan style=\"font-size:12px;font-family:SimSun;\"\u003e；\u003c/span\u003e\u003cspan style='font-size:12px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp; \u0026nbsp;\u003c/span\u003e\u003cspan style=\"font-size:12px;font-family:SimSun;\"\u003e②\u003c/span\u003e\u003cspan style='font-size:12px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;Top 5 Factor Highlighting\u003cbr\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Machine learning, Medical science popularization short videos, Prediction models, Non-medical factors","lastPublishedDoi":"10.21203/rs.3.rs-4742337/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4742337/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo summarize the current shooting trends of this type of video, discuss the effect of non-medical factors on the spread of videos, and develop prediction models using machine learning (ML) algorithms.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe searched and filtered medical science popularization videos on TikTok, then labeled non-medical features as variables and record the number of \u0026ldquo;Thumb-Up\u0026rdquo;, \u0026ldquo;Comment\u0026rdquo;, \u0026ldquo;Share\u0026rdquo; and \u0026ldquo;Collection\u0026rdquo; as outcome indicators. A total of 286 samples and 34 variables were included in the construction of the ML model, and 13 algorithms were employed with the area under the curve (AUC) for performance assessment and a ten-fold cross-validation for accuracy testing.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eIn the quantitative analysis of the 4 outcome indicators, we identified significant disparities among different videos. Subsequently, five best-performing models were ultimately confirmed to predict the reasons for differences: \u0026ldquo;Thumb-Up\u0026rdquo; RF Model (AUC\u0026thinsp;=\u0026thinsp;0.7331), \u0026ldquo;Collection\u0026rdquo; RF Model (AUC\u0026thinsp;=\u0026thinsp;0.7439), \u0026ldquo;Share\u0026rdquo; RF Model (AUC\u0026thinsp;=\u0026thinsp;0.7077), \u0026ldquo;Comment\u0026rdquo; RF Model (AUC\u0026thinsp;=\u0026thinsp;0.7960), \u0026ldquo;Comment\u0026rdquo; BNB Model (AUC\u0026thinsp;=\u0026thinsp;0.7844). By ML models, the video duration, title and description length, shooting location emerged and body language as the most five crucial parameters across all five models.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eML models demonstrated superior performance in predicting the influence of non-medical factors on the spread of medical science popularization videos. The weight of these variables will provide valuable guidance for video preparation. This study contributes to the dissemination and acceptance of medical science popularization videos by the public, thereby promoting health education and enhancing public awareness and competence in healthcare.\u003c/p\u003e","manuscriptTitle":"Machine learning prediction models for the popularization and dissemination of medical science popularization videos","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-19 06:45:57","doi":"10.21203/rs.3.rs-4742337/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b65e72e7-11d1-4499-a268-45fe74210b84","owner":[],"postedDate":"August 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":35961244,"name":"Health sciences/Health care"},{"id":35961245,"name":"Health sciences/Health care/Health services"},{"id":35961246,"name":"Health sciences/Health care/Public health"}],"tags":[],"updatedAt":"2024-12-09T04:09:05+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-19 06:45:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4742337","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4742337","identity":"rs-4742337","version":["v1"]},"buildId":"J0_U0BvcaRcwD8yVFaRlm","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}