Context-Aware Fusion and Adaptive Peak Weighting: A Deep Learning Framework for Scenic Area Demand Forecasting

Context-Aware Fusion and Adaptive Peak Weighting: A Deep Learning Framework for Scenic Area Demand Forecasting | 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 Context-Aware Fusion and Adaptive Peak Weighting: A Deep Learning Framework for Scenic Area Demand Forecasting Caili Gong, Shaoxuan Liu, Yongfeng Wei, Jianxiu Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9506657/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract While unstructured electronic word-of-mouth increasingly dictates tourist decision-making, contemporary forecasting models,tethered to structured data, fail to integrate quantitative sentiment features within dynamic contexts. Furthermore, traditionalmodels suffer from chronic “peak attenuation” in volatile natural scenic areas due to global error optimization constraints.To bridge these gaps, a deep demand forecasting system driven by context-aware fusion and adaptive peak weighting isproposed. Specifically, sentiment trajectories are quantified through a multi-task regression model (RoBERTa-MSR) withBayesian smoothing, then adaptively modulated by a Context-Aware Weighting Module (CAWM) using meteorological andtemporal priors to capture environmental triggers. For extrapolation, the CAPW-Autoformer network is constructed, utilizinga composite training strategy—integrating Adaptive Peak Weighting (APW) and the Concordance Correlation Coefficient(CCC)—to mitigate peak attenuation. Experimental results demonstrate the framework’s superiority: sentiment quantificationimproves Pearson’s r by 8.80%, while demand forecasting yields a 7.24% increase in Pearson’s r and a 16.86% rise in R2,with RMSE and MAE reduced by 23.09% and 17.90%, respectively. This approach enables high-fidelity tracking of extremepeaks and deconstructs emotional attention reversal patterns, establishing a robust quantitative paradigm for smart tourismmanagement in high-volatility environments. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 14 May, 2026 Reviewers agreed at journal 13 May, 2026 Reviewers invited by journal 13 May, 2026 Editor assigned by journal 08 May, 2026 Editor invited by journal 03 May, 2026 Submission checks completed at journal 28 Apr, 2026 First submitted to journal 28 Apr, 2026 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-9506657","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":640150959,"identity":"cdd31de8-c916-4ead-9928-6e017a1c03fa","order_by":0,"name":"Caili Gong","email":"","orcid":"","institution":"Inner Mongolia University","correspondingAuthor":false,"prefix":"","firstName":"Caili","middleName":"","lastName":"Gong","suffix":""},{"id":640150967,"identity":"321bf9bd-226a-437b-ba69-e79895171a32","order_by":1,"name":"Shaoxuan Liu","email":"","orcid":"","institution":"Inner Mongolia University","correspondingAuthor":false,"prefix":"","firstName":"Shaoxuan","middleName":"","lastName":"Liu","suffix":""},{"id":640150971,"identity":"b9b99f7e-bcb9-46cf-9d51-ddf4a734a114","order_by":2,"name":"Yongfeng Wei","email":"","orcid":"","institution":"Inner Mongolia University","correspondingAuthor":false,"prefix":"","firstName":"Yongfeng","middleName":"","lastName":"Wei","suffix":""},{"id":640150972,"identity":"11eced58-e536-420d-b975-d8e8d74af07e","order_by":3,"name":"Jianxiu Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYBACPmaGBIYPBmC2AXFa2IBaGGeQpgWImXkYSNLCzvBM2qZgW2IDe/M2CYaaO0Q5LNk4x+B2YgPPsTIJhmPPiNKS+BisRSLHTIKx4TBRWhIOW4C0yL8hXkviYwawLTzEa0k27DG4bdzGk1ZskXCMCC38/GfSJH78uS3bz354440PNURoYWDgSYBYByISiNHAwMB+gDh1o2AUjIJRMHIBAL6TMPULgFaAAAAAAElFTkSuQmCC","orcid":"","institution":"Inner Mongolia University","correspondingAuthor":true,"prefix":"","firstName":"Jianxiu","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2026-04-23 12:23:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9506657/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9506657/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109296323,"identity":"fe1d4376-ba16-44de-bb00-ed34a38671b4","added_by":"auto","created_at":"2026-05-15 08:46:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5865615,"visible":true,"origin":"","legend":"","description":"","filename":"CAPWAutoformerV2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9506657/v1_covered_8c825596-91a0-4204-9728-ed3b6d895ad6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eContext-Aware Fusion and Adaptive Peak Weighting: A Deep Learning Framework for Scenic Area Demand Forecasting\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9506657/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9506657/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While unstructured electronic word-of-mouth increasingly dictates tourist decision-making, contemporary forecasting models,tethered to structured data, fail to integrate quantitative sentiment features within dynamic contexts. Furthermore, traditionalmodels suffer from chronic “peak attenuation” in volatile natural scenic areas due to global error optimization constraints.To bridge these gaps, a deep demand forecasting system driven by context-aware fusion and adaptive peak weighting isproposed. Specifically, sentiment trajectories are quantified through a multi-task regression model (RoBERTa-MSR) withBayesian smoothing, then adaptively modulated by a Context-Aware Weighting Module (CAWM) using meteorological andtemporal priors to capture environmental triggers. For extrapolation, the CAPW-Autoformer network is constructed, utilizinga composite training strategy—integrating Adaptive Peak Weighting (APW) and the Concordance Correlation Coefficient(CCC)—to mitigate peak attenuation. Experimental results demonstrate the framework’s superiority: sentiment quantificationimproves Pearson’s r by 8.80%, while demand forecasting yields a 7.24% increase in Pearson’s r and a 16.86% rise in R2,with RMSE and MAE reduced by 23.09% and 17.90%, respectively. This approach enables high-fidelity tracking of extremepeaks and deconstructs emotional attention reversal patterns, establishing a robust quantitative paradigm for smart tourismmanagement in high-volatility environments.","manuscriptTitle":"Context-Aware Fusion and Adaptive Peak Weighting: A Deep Learning Framework for Scenic Area Demand Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-14 16:36:16","doi":"10.21203/rs.3.rs-9506657/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"305660941594784732490227598136083556658","date":"2026-05-14T07:45:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161970002598464345306717693882586561057","date":"2026-05-13T09:38:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-13T09:10:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-08T09:01:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-04T03:59:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-28T15:55:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-28T13:49:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f8c41e04-c0fa-4706-b033-a1c7b4ea9f5f","owner":[],"postedDate":"May 14th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"305660941594784732490227598136083556658","date":"2026-05-14T07:45:18+00:00","index":47,"fulltext":""},{"type":"reviewerAgreed","content":"161970002598464345306717693882586561057","date":"2026-05-13T09:38:10+00:00","index":46,"fulltext":""},{"type":"reviewersInvited","content":"8","date":"2026-05-13T09:10:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-08T09:01:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-04T03:59:03+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":68150625,"name":"Physical sciences/Engineering"},{"id":68150626,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-14T16:36:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-14 16:36:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9506657","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9506657","identity":"rs-9506657","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}