Assessing Sarcasm Dataset Quality

Assessing Sarcasm Dataset Quality | 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 Assessing Sarcasm Dataset Quality Girma Yohannis Bade, Olga Kolesnikova, Jose Luis Oropeza This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7541663/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 Artificial intelligence (AI) models depend on high-quality data to maintain accuracy and ensure safe deployment. However, the presence of sarcasm in sentiment analysis (SA) poses a unique challenge due to its inherently ambiguous and context-dependent nature, significantly impacting model performance. In this context, sarcasm detection plays a pivotal role in improving SA accuracy. While significant effort has been exerted, most existing sarcasm detection systems face substantial challenges due to poorly annotated datasets and the inherently complex nature of sarcastic language. To address this, we evaluate sarcasm data quality by benchmarking uniformly parameterized models across four distinct datasets: SARC, SemEval2022, NewsHeadline, and Multimodal. We conduct extensive evaluations using a three-model hierarchy: statistical machine learning, deep learning, and transfer learning models, alongside TF-IDF vectorization and word embeddings for text representation.To mitigate bias arising from class imbalance and unequal data distribution, we applied two resampling techniques—oversampling and undersampling—before conducting our experiments. Our findings reveal that the NewsHeadline dataset achieves superior performance, with RoBERTa attaining an F1-score of 0.93. Based on these insights, we compile and release a refined Sarcasm-Quality (SQ) dataset to advance future research in sarcasm-aware NLP systems. Physical sciences/Engineering Physical sciences/Mathematics and computing Sarcasm detection natural language processing deep learning machine learning state-of-the-art Full Text Additional Declarations No competing interests reported. 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-7541663","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":527670555,"identity":"041d1148-5b23-4408-b323-26bce8dd5c12","order_by":0,"name":"Girma Yohannis Bade","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYDACZhBRIcFj394AZBhYEKvljI2cAc8BkBYJIm1ibEszNpBIADGJ0CLvzvt0wwe2w4nbJZ9f3fCjQIKBv707Aa8Ww8PsZjdn8BxO3Dk7p+xmD9BhEmfObsCvpZmN7TaPxOHEhts5aTd4gFoMJHKJ0PLHAKjl5pm0m3+I0SLPDNTCkAD0/g32Y7eJssUAqOVmzwEbOcmeHLbbMgYSPAT9It9/jO3Gz38SPPzsx5/dfPPHRo6/vZeALQfgTB4DMIlXOdiWBjiT/QFB1aNgFIyCUTAyAQD5Ckhx+45ewwAAAABJRU5ErkJggg==","orcid":"","institution":"Centro de Investigación en Computación(CIC), Instituto Politécnico Nacional(IPN)","correspondingAuthor":true,"prefix":"","firstName":"Girma","middleName":"Yohannis","lastName":"Bade","suffix":""},{"id":527670556,"identity":"671df084-eb99-4caf-a8cc-cd445cf1042a","order_by":1,"name":"Olga Kolesnikova","email":"","orcid":"","institution":"Centro de Investigación en Computación(CIC), Instituto Politécnico Nacional(IPN)","correspondingAuthor":false,"prefix":"","firstName":"Olga","middleName":"","lastName":"Kolesnikova","suffix":""},{"id":527670557,"identity":"522f0a8c-b898-4e27-94d7-cf8db784b220","order_by":2,"name":"Jose Luis Oropeza","email":"","orcid":"","institution":"Centro de Investigación en Computación(CIC), Instituto Politécnico Nacional(IPN)","correspondingAuthor":false,"prefix":"","firstName":"Jose","middleName":"Luis","lastName":"Oropeza","suffix":""}],"badges":[],"createdAt":"2025-09-05 07:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7541663/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7541663/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93417107,"identity":"c3f84d2a-f9d2-49be-89f3-1cfc3d9e9c4f","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4955,"visible":true,"origin":"","legend":"","description":"","filename":"9d691e6d9da54b4a9397cbb2fdfc5db4.json","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/5c73c1b7b86c810ae78d59f3.json"},{"id":93417112,"identity":"090ae4bb-94a0-4017-bced-cf8b4b7b4ef8","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105166,"visible":true,"origin":"","legend":"","description":"","filename":"9d691e6d9da54b4a9397cbb2fdfc5db41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/ea55ae01619c74918dcd7a1f.xml"},{"id":93418343,"identity":"4469201d-5daf-4326-8455-2b8021400688","added_by":"auto","created_at":"2025-10-13 15:48:02","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":552822,"visible":true,"origin":"","legend":"","description":"","filename":"Scientificreportsupdate2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/bbeb261d29d54396f1d36df6.pdf"},{"id":93417110,"identity":"3b05e5b1-b811-4fff-9557-2180b9827c63","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27870,"visible":true,"origin":"","legend":"","description":"","filename":"afteroversample.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/2261227373918b631ee52eaa.png"},{"id":93416719,"identity":"e0094a3f-0e2f-4923-908b-ba61fb3d4be7","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33281,"visible":true,"origin":"","legend":"","description":"","filename":"aia.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/74ad673cc03c5990f06e7d92.png"},{"id":93416722,"identity":"c0d7849a-73d7-4ee7-973c-7ad8a573cef0","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41676,"visible":true,"origin":"","legend":"","description":"","filename":"dataquality.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/0e88e38331ed1b799d895564.png"},{"id":93416720,"identity":"0590dd39-e568-4adc-a55b-d73330430813","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21128,"visible":true,"origin":"","legend":"","description":"","filename":"embedding1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/a399fa0f9471e526c2d2ad41.png"},{"id":93417109,"identity":"7dba43a4-f02f-4934-878a-226cd3d69fb8","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"eps","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/dbcc990c59e3254be2242e8a.eps"},{"id":93416726,"identity":"ca64c5a0-ac53-4f9e-b374-9d408e5999e5","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16620,"visible":true,"origin":"","legend":"","description":"","filename":"evarch3.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/b72000afb39e5316d59ae337.png"},{"id":93417977,"identity":"82643b12-a82f-46ea-a9ab-dfa460d63da2","added_by":"auto","created_at":"2025-10-13 15:40:02","extension":"eps","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/b2ac4737a13170ff91dbdc67.eps"},{"id":93416729,"identity":"2e8f4a69-07fb-42c2-a730-dd729a5ffa98","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"languageData.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/14f00cfd01b079d7d54a6f13.png"},{"id":93416740,"identity":"90372dec-c1ce-4ea2-9d72-902bbfcfae7f","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167328,"visible":true,"origin":"","legend":"","description":"","filename":"llm.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/c565108eed7a16ce895f44c1.png"},{"id":93417982,"identity":"9de04f45-4dcf-4a92-8cd5-c27b26461d6c","added_by":"auto","created_at":"2025-10-13 15:40:03","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7872,"visible":true,"origin":"","legend":"","description":"","filename":"oversampling.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/487cbdc7fd86388343a5cc3e.png"},{"id":93416728,"identity":"48a0b5a4-1f38-4be8-b23d-a9896fb916cd","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106105,"visible":true,"origin":"","legend":"","description":"","filename":"pie1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/58aa549c183b7d8968fabda5.png"},{"id":93417113,"identity":"1fe39013-ddac-4320-83c8-5ac2920ebc85","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27501,"visible":true,"origin":"","legend":"","description":"","filename":"pieupdate.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/00c9b764381e42f2d9e74e37.png"},{"id":93416737,"identity":"d017ab03-51a9-4807-81d1-b7c50c4e9e85","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":275284,"visible":true,"origin":"","legend":"","description":"","filename":"plot.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/65282b4d18e3697714cec6fe.png"},{"id":93416730,"identity":"c58fd43f-5b48-4802-9b80-7af99d5ff82e","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15366,"visible":true,"origin":"","legend":"","description":"","filename":"qualit11.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/5256471907a6e186c19caeb4.png"},{"id":93416738,"identity":"27d1c4f3-8036-4d1f-837f-8d5dca3c3191","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"pdf","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":185549,"visible":true,"origin":"","legend":"","description":"","filename":"responseletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/6cf5312ccfe6b30a31aea12b.pdf"},{"id":93416733,"identity":"4b0371b3-7366-4b28-8b72-548873a80f18","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"pdf","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":185549,"visible":true,"origin":"","legend":"","description":"","filename":"responseletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/a761dab6bb3c089121142912.pdf"},{"id":93417130,"identity":"3bb99de2-ff0a-4ee1-979a-8eb1344fcb64","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147148,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/8363b96c30b004f7eef92a94.bst"},{"id":93416772,"identity":"157badcb-4aa0-4c82-8f1a-55cce022e1cf","added_by":"auto","created_at":"2025-10-13 15:24:04","extension":"bst","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30423,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/9e1ddf46e01328bf912b0bb7.bst"},{"id":93416748,"identity":"dbf25f69-43da-4318-a601-3526a74b7386","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"pdf","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":390370,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/fc5a3a1eaea3e85a6ebf7ff2.pdf"},{"id":93416742,"identity":"ec28ff86-41e3-4338-b96c-3c10e95b3a17","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"bst","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35733,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/a45dcc89880a0d37efaddc71.bst"},{"id":93417117,"identity":"54908ae3-2596-497c-acdf-c003338a8903","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"bst","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40398,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/892c4227c28df3ddc8802588.bst"},{"id":93417114,"identity":"fbd03e4d-fb47-4801-a4a0-77460810b2f1","added_by":"auto","created_at":"2025-10-13 15:32:02","extension":"cls","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55339,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/fe9d10ba3795a128c0346f32.cls"},{"id":93416735,"identity":"47f371fe-d61a-4a12-8389-be6fcb61ae74","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"bst","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64140,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/bf171e31cef5f1362f548e3f.bst"},{"id":93416736,"identity":"3cc505e1-8159-4156-adf3-fcd60a72f7aa","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"bst","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64141,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/731dee82a379a3fea36bc93d.bst"},{"id":93417125,"identity":"334f3fad-22f2-4c97-aeb3-4416586a4f85","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"bst","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38349,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/e442d573c8a2c5e588a552b0.bst"},{"id":93417131,"identity":"2016e015-b99c-4d10-8912-266e95719f8a","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"bst","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41304,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouver.bst","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/1f61593ed2a4b29458a2973c.bst"},{"id":93416731,"identity":"18cd8da1-ee45-4837-8fe0-7b6e14afbd77","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17154,"visible":true,"origin":"","legend":"","description":"","filename":"trendupdate.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/5439a44e1fb0a7ec405efddb.png"},{"id":93416760,"identity":"cd7ca10f-879a-4b0f-b6c8-b70dfd9ef04f","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6592,"visible":true,"origin":"","legend":"","description":"","filename":"undersampling.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/848ab9e5c32c211f5bf4fd7f.png"},{"id":93417981,"identity":"bcbc849b-e38f-44fd-ad58-d1b075d153c0","added_by":"auto","created_at":"2025-10-13 15:40:03","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26180,"visible":true,"origin":"","legend":"","description":"","filename":"undersampling1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/09ab0653a304b833ec8c4d82.png"},{"id":93417115,"identity":"607e1a5a-8ab6-479f-ab7d-e7063e0d3b86","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"pdf","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":415247,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/c1450a5268a8911e7c558581.pdf"},{"id":93416746,"identity":"adb8a25d-4b2c-4489-a703-efb4aa882b9c","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48074,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineSRarch.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/f2de8f988b1154b4eb3b49df.png"},{"id":93417120,"identity":"2e9b3ae9-65cc-4a9e-acaf-0fa8095e48a6","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22805,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineafteroversample.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/0de2a051bfe8933d8b23ba19.png"},{"id":93416763,"identity":"2a069848-93e1-4548-a8e3-f2970c413bd5","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29109,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineaia.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/509436752516cdc85484163b.png"},{"id":93416753,"identity":"f464d0f5-4fb6-4b81-a2cd-3c7bdc5a4d63","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18653,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinebeforeimbalance.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/b628ea18d9d1effbc2124332.png"},{"id":93416750,"identity":"d19b1b8d-64eb-41dc-b40b-da0f768d81df","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40048,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedataquality.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/63547dcc4986dc1e113d5033.png"},{"id":93416739,"identity":"a9646c0f-15a3-403b-b25d-8f9c0e0468ba","added_by":"auto","created_at":"2025-10-13 15:24:02","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38560,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineembedding.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/ebea3526f67d99cf4a29041d.png"},{"id":93417127,"identity":"a6042634-7061-4504-b390-32e1a99ecbe9","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23112,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineembedding1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/0894c27c1e612a5d04712d86.png"},{"id":93417980,"identity":"70941723-3c4d-46fd-ba7f-b359c1c6664f","added_by":"auto","created_at":"2025-10-13 15:40:03","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14479,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineevarch3.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/4316ea3e94d8ee8ab49c72a2.png"},{"id":93416768,"identity":"7e888dd6-748c-48bc-a7fe-dda0eab6d382","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16453,"visible":true,"origin":"","legend":"","description":"","filename":"OnlinelanguageData.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/0837a6505853eebf37d13cf6.png"},{"id":93416769,"identity":"f68652e1-d505-4eeb-b791-6e2d739db944","added_by":"auto","created_at":"2025-10-13 15:24:04","extension":"png","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":144622,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinellm.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/5df63e7c544fa7f3331c9afb.png"},{"id":93416770,"identity":"61c116bd-9b0f-481d-a24a-e452a9c019a4","added_by":"auto","created_at":"2025-10-13 15:24:04","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14395,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineoversampleresult.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/ee072e358aec819ef7879a98.png"},{"id":93416743,"identity":"65ff1ebe-7e58-45d1-bd20-206e96343030","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8673,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineoversampling.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/152367857a7a4a7feb84d212.png"},{"id":93417129,"identity":"8cec2757-b4ed-46fe-a76d-c5842b59be31","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"png","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13683,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineperUnder.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/cf940a6390ae5fbc26251fdb.png"},{"id":93417124,"identity":"5c5235cc-295e-49f2-9484-a5a7c8bb230e","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"png","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94337,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinepie1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/2fecdd0701619bcf5559fd41.png"},{"id":93417979,"identity":"18e568ec-df08-4d04-b80f-531ccb32d637","added_by":"auto","created_at":"2025-10-13 15:40:03","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28663,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinepieupdate.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/1027586ddc4b0d492516d2ca.png"},{"id":93416773,"identity":"907df664-f552-45b7-a762-29cebcbe1b3f","added_by":"auto","created_at":"2025-10-13 15:24:04","extension":"png","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":239893,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineplot.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/2c07ca986a3fff997dc469f4.png"},{"id":93416764,"identity":"dfe478f8-f376-473a-b6f2-0799305b7369","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12399,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinequalit11.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/19d92c12bf197f9024724882.png"},{"id":93416767,"identity":"b8efb3bc-01a9-4bbf-af6b-3b6e1e517dbc","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15924,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinetrendupdate.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/c3a92c4820fdeb09cb6ba8c8.png"},{"id":93416762,"identity":"f7f3ff20-45bd-454b-9a71-609ce555fa35","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"png","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7367,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineundersampling.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/0d4a52e64ebd7b5365b8689f.png"},{"id":93417119,"identity":"b5c755dc-4414-4eb2-bea3-2bacc1bb8279","added_by":"auto","created_at":"2025-10-13 15:32:03","extension":"png","order_by":57,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22309,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineundersampling1.png","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/9d1d46da5e3d83a657b23abd.png"},{"id":93416747,"identity":"5e147814-1d8d-4a7c-aaa2-e645d1b00757","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"xml","order_by":58,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114858,"visible":true,"origin":"","legend":"","description":"","filename":"9d691e6d9da54b4a9397cbb2fdfc5db41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/836b9f3242515a5bda7d3968.xml"},{"id":93416758,"identity":"3310eb5f-0ef4-4288-877b-d2ae8c85edfe","added_by":"auto","created_at":"2025-10-13 15:24:03","extension":"html","order_by":59,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":118441,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1/9f1e0b7d874e0aa8b7691d95.html"},{"id":101752210,"identity":"5c9a142b-dbbc-4c05-8216-1ba1a549839c","added_by":"auto","created_at":"2026-02-03 10:26:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":447484,"visible":true,"origin":"","legend":"","description":"","filename":"Scientificreportsupdate2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541663/v1_covered_6691061a-9735-493a-aab3-202fea75cffd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Assessing Sarcasm Dataset Quality","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Sarcasm detection, natural language processing, deep learning, machine learning, state-of-the-art","lastPublishedDoi":"10.21203/rs.3.rs-7541663/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7541663/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial intelligence (AI) models depend on high-quality data to maintain accuracy and ensure safe deployment. However, the presence of sarcasm in sentiment analysis (SA) poses a unique challenge due to its inherently ambiguous and context-dependent nature, significantly impacting model performance. In this context, sarcasm detection plays a pivotal role in improving SA accuracy. While significant effort has been exerted, most existing sarcasm detection systems face substantial challenges due to poorly annotated datasets and the inherently complex nature of sarcastic language. To address this, we evaluate sarcasm data quality by benchmarking uniformly parameterized models across four distinct datasets: SARC, SemEval2022, NewsHeadline, and Multimodal. We conduct extensive evaluations using a three-model hierarchy: statistical machine learning, deep learning, and transfer learning models, alongside TF-IDF vectorization and word embeddings for text representation.To mitigate bias arising from class imbalance and unequal data distribution, we applied two resampling techniques—oversampling and undersampling—before conducting our experiments. Our findings reveal that the NewsHeadline dataset achieves superior performance, with RoBERTa attaining an F1-score of 0.93. Based on these insights, we compile and release a refined Sarcasm-Quality (SQ) dataset to advance future research in sarcasm-aware NLP systems.\u003c/p\u003e","manuscriptTitle":"Assessing Sarcasm Dataset Quality","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-13 15:23:52","doi":"10.21203/rs.3.rs-7541663/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":"f33086f6-dbad-4f60-bb0b-989fa9b26f46","owner":[],"postedDate":"October 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56090400,"name":"Physical sciences/Engineering"},{"id":56090401,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-01-30T13:56:47+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-13 15:23:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7541663","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7541663","identity":"rs-7541663","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}