Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework

Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework | 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 Research Article Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework Zoya Maqsood, Seemab Latif, Ahmad Salman, Rabia Latif This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4609260/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 Aspect-Based Sentiment Analysis (ABSA) is pivotal for diverse applications but faces significant hurdles in under-resourced languages like Urdu, primarily due to the absence of a comprehensive, annotated benchmark corpus. This study tackles this gap by introducing a novel Weakly Supervised technique to construct a benchmark dataset tailored for Urdu ABSA, addressing public availability, domain coverage, and annotation comprehensiveness. Our dataset encompasses detailed annotations across all ABSA dimensions i.e. aspect, opinion, sentiment polarity and category. Through a comparative analysis involving Large Language Models (LLMs), human annotations, and pre-trained models based on expertly curated datasets, we demonstrate the dataset’s complexity and the nuanced nature of ABSA in Urdu, as reflected in the challenging outcomes of ABSA subtasks using a basic LSTM approach. This research not only advances Urdu ABSA techniques but also illuminates the broader challenges of Opinion Mining in under-resourced languages, setting a precedent for future work in this critical area. Aspect-Based Sentiment Analysis (ABSA) Weakly Supervised Technique Benchmark Dataset Urdu Language Sentiment Polarity 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-4609260","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":321332743,"identity":"cbe2f84b-fa3f-4d1b-9765-94a6a6e7627f","order_by":0,"name":"Zoya Maqsood","email":"","orcid":"","institution":"National University of Sciences and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zoya","middleName":"","lastName":"Maqsood","suffix":""},{"id":321332744,"identity":"02ae9b8c-d30f-40f9-8758-6a9704c42961","order_by":1,"name":"Seemab Latif","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYLACxgYGGRD54QNMhAeIJQho4WFgY2ycOYNELQyMs3mI0SLf3nx0w88dDDz885sbm23+2Mjx9x9gfPC2jSFPsgG7FoMzx9Ju9p5h4JE4xtjYnNuWZixxI4HZcG4bQ7E0DlsMJHLMbvC2AV1yjLH9cW7D4cQNEgxs0kCRxHm4HDb//bebf4Fa5EG2WPz5X7+B/wD7b3xaGG7wsN0G2WIA0sLAdiDBgCGBjRmkZTYuh51JM7ste0aCx/BYYmNjb1uy4Ywbic2Sc85JFOPyvnz74Wc33+6wkZM7fPxhw48/dvL8/YcPfnhTZpMncQCXy8AAJQ4YQcZLJODVgBWQoWUUjIJRMAqGKQAAvEhbuk4pdCIAAAAASUVORK5CYII=","orcid":"","institution":"National University of Sciences and Technology","correspondingAuthor":true,"prefix":"","firstName":"Seemab","middleName":"","lastName":"Latif","suffix":""},{"id":321332745,"identity":"d11ee691-34c9-4a41-830e-ca5b26b216d7","order_by":2,"name":"Ahmad Salman","email":"","orcid":"","institution":"National University of Sciences and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ahmad","middleName":"","lastName":"Salman","suffix":""},{"id":321332746,"identity":"e5fcba79-6bfa-40ae-afdb-a8de0f5c0c2e","order_by":3,"name":"Rabia Latif","email":"","orcid":"","institution":"Prince Sultan University","correspondingAuthor":false,"prefix":"","firstName":"Rabia","middleName":"","lastName":"Latif","suffix":""}],"badges":[],"createdAt":"2024-06-20 05:22:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4609260/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4609260/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65040019,"identity":"c195a95f-a2bf-46de-b66f-929096d6ee70","added_by":"auto","created_at":"2024-09-23 02:59:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":980187,"visible":true,"origin":"","legend":"","description":"","filename":"ZoyaSpringerJML.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4609260/v1_covered_31c2305f-8545-488b-aab4-f413df96e1a6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework","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":"Aspect-Based Sentiment Analysis (ABSA), Weakly Supervised Technique, Benchmark Dataset, Urdu Language, Sentiment Polarity","lastPublishedDoi":"10.21203/rs.3.rs-4609260/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4609260/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Aspect-Based Sentiment Analysis (ABSA) is pivotal for diverse applications but faces significant hurdles in under-resourced languages like Urdu, primarily due to the absence of a comprehensive, annotated benchmark corpus. This study tackles this gap by introducing a novel Weakly Supervised technique to construct a benchmark dataset tailored for Urdu ABSA, addressing public availability, domain coverage, and annotation comprehensiveness. Our dataset encompasses detailed annotations across all ABSA dimensions i.e. aspect, opinion, sentiment polarity and category. Through a comparative analysis involving Large Language Models (LLMs), human annotations, and pre-trained models based on expertly curated datasets, we demonstrate the dataset’s complexity and the nuanced nature of ABSA in Urdu, as reflected in the challenging outcomes of ABSA subtasks using a basic LSTM approach. This research not only advances Urdu ABSA techniques but also illuminates the broader challenges of Opinion Mining in under-resourced languages, setting a precedent for future work in this critical area.","manuscriptTitle":"Towards Robust Urdu Aspect-based Sentiment Analysis through Weakly-Supervised Annotation Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-11 06:50:35","doi":"10.21203/rs.3.rs-4609260/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":"4dcc9385-6d11-4da8-aac9-5daaa1dc7e96","owner":[],"postedDate":"July 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-09-23T02:51:20+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-11 06:50:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4609260","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4609260","identity":"rs-4609260","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}