{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T12:28:58Z","timestamp":1765974538858,"version":"3.41.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The COVID-19 pandemic resulted in over 600 million cases worldwide, and significantly impacted both physical and mental health, fostering widespread anxiety and fear. Consequently, the extensive use of online social networks to express emotions made sentiment analysis a crucial tool for understanding public sentiment. Traditionally, sentiment analysis in the Urdu language has focused on sentence-level analysis. However, aspect-level sentiment analysis is increasingly important and remains underexplored due to the challenges of the costly and time-consuming manual dataset annotation process. This study presents an innovative bilingual aspect-based sentiment analysis for Urdu and Roman Urdu using unsupervised methods. For Urdu, a syntactic rule-based approach achieves an accuracy of 83% in extracting aspect terms, marking a 5% improvement in F1-score over existing methods. For Roman Urdu, the study employs collocation patterns and topic modeling to identify and categorize key aspects, resulting in a perplexity score of \u20137 and a coherence score of 41. The results not only demonstrate the semantic coherence of the identified categories but also represent a significant advancement in aspect-level sentiment analysis by eliminating the need for manual annotation. This study offers new insights into the sentiments expressed during the pandemic, providing valuable feedback for policymakers and health organizations.<\/jats:p>","DOI":"10.1371\/journal.pone.0317562","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T17:42:41Z","timestamp":1749836561000},"page":"e0317562","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["BI-SENT: bilingual aspect-based sentiment analysis of COVID-19 Tweets in Urdu language"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2526-9899","authenticated-orcid":true,"given":"Ehtesham","family":"Hashmi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amna","family":"Altaf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Waqas","family":"Anwar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0114-0887","authenticated-orcid":true,"given":"Muhammad Hasan","family":"Jamal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Usama Ijaz","family":"Bajwa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"key":"pone.0317562.ref001","doi-asserted-by":"crossref","first-page":"596201","DOI":"10.3389\/fcimb.2021.596201","article-title":"Wuhan to world: the COVID-19 pandemic","volume":"11","author":"A Kumar","year":"2021","journal-title":"Front Cell Infect Microbiol"},{"issue":"1","key":"pone.0317562.ref002","doi-asserted-by":"crossref","first-page":"3737","DOI":"10.1038\/s41467-021-24115-7","article-title":"Association of social distancing and face mask use with risk of COVID-19","volume":"12","author":"S Kwon","year":"2021","journal-title":"Nat Commun"},{"key":"pone.0317562.ref003","volume-title":"The impact of covid-19 on student equity and inclusion: supporting vulnerable students during school closures and school re-openings","author":"L Cerna","year":"2020"},{"key":"pone.0317562.ref004","unstructured":"Mcclain C, Vogels E, Perrin R, Sechopoulos S, Rainie L, Atske S.: The Internet and the pandemic."},{"issue":"1","key":"pone.0317562.ref005","doi-asserted-by":"crossref","first-page":"16","DOI":"10.3390\/bdcc7010016","article-title":"Arabic Tweets-based sentiment analysis to investigate the impact of COVID-19 in KSA: a deep learning approach","volume":"7","author":"A Alqarni","year":"2023","journal-title":"BDCC"},{"key":"pone.0317562.ref006","doi-asserted-by":"crossref","unstructured":"Sun T, Jing L, Wei Y, Song X, Cheng Z, Nie L.: Dual consistency-enhanced semi-supervised sentiment analysis towards covid-19 tweets. IEEE Trans Knowl Data Eng. 2023.","DOI":"10.1109\/TKDE.2023.3270940"},{"key":"pone.0317562.ref007","doi-asserted-by":"crossref","first-page":"114155","DOI":"10.1016\/j.eswa.2020.114155","article-title":"Sentiment analysis and its applications in fighting COVID-19 and infectious diseases: a systematic review","volume":"167","author":"AH Alamoodi","year":"2021","journal-title":"Expert Syst Appl"},{"issue":"1","key":"pone.0317562.ref008","first-page":"1","article-title":"Social media sentiment analysis based on covid-19","volume":"5","author":"L Nemes","year":"2021","journal-title":"J Inf Telecommun"},{"issue":"1","key":"pone.0317562.ref009","first-page":"012045","article-title":"Sentiment analysis of COVID-19 vaccine in Indonesia using Na\u00efve Bayes Algorithm","volume":"1088","author":"M Ritonga","year":"2021","journal-title":"IOP Conf Ser: Mater Sci Eng"},{"key":"pone.0317562.ref010","doi-asserted-by":"crossref","first-page":"107242","DOI":"10.1016\/j.knosys.2021.107242","article-title":"A novel fusion-based deep learning model for sentiment analysis of COVID-19 tweets","volume":"228","author":"ME Basiri","year":"2021","journal-title":"Knowl Based Syst"},{"key":"pone.0317562.ref011","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.ins.2019.02.064","article-title":"Aspect based fine-grained sentiment analysis for online reviews","volume":"488","author":"F Tang","year":"2019","journal-title":"Information Sciences"},{"key":"pone.0317562.ref012","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.aci.2019.11.003","article-title":"Aspect-based sentiment analysis using smart government review data","volume":"20","author":"O Alqaryouti","year":"2020","journal-title":"ACI"},{"key":"pone.0317562.ref013","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1109\/FiCloud.2015.62","article-title":"Human annotated Arabic dataset of book reviews for aspect based sentiment analysis.","volume-title":"2015 3rd International Conference on Future Internet of Things and Cloud","author":"M Al-Smadi","year":"2015"},{"issue":"6","key":"pone.0317562.ref014","doi-asserted-by":"crossref","first-page":"6939","DOI":"10.1007\/s11042-018-6445-z","article-title":"A survey on sentiment analysis and opinion mining for social multimedia","volume":"78","author":"Z Li","year":"2018","journal-title":"Multimed Tools Appl"},{"key":"pone.0317562.ref015","doi-asserted-by":"crossref","first-page":"102135","DOI":"10.1109\/ACCESS.2022.3208164","article-title":"Deep learning based cross domain sentiment classification for Urdu language","volume":"10","author":"A Altaf","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0317562.ref016","first-page":"1","article-title":"An overview of lexicon-based approach for sentiment analysis","volume-title":"In: 2018 3rd International Electrical Engineering Conference (IEEC 2018)","author":"A Sadia","year":"2018"},{"key":"pone.0317562.ref017","first-page":"32","article-title":"Lexicon-based sentiment analysis of Urdu text using sentiunits","volume-title":"In: Advances in Artificial Intelligence: 9th Mexican International Conference on Artificial Intelligence, MICAI 2010, Pachuca, Mexico, 2010 Nov 8\u201313, Part I 9","author":"AZ Syed","year":"2010"},{"issue":"4","key":"pone.0317562.ref018","doi-asserted-by":"crossref","first-page":"2521","DOI":"10.1007\/s10462-019-09740-5","article-title":"Effective lexicon-based approach for Urdu sentiment analysis","volume":"53","author":"N Mukhtar","year":"2019","journal-title":"Artif Intell Rev"},{"issue":"3","key":"pone.0317562.ref019","doi-asserted-by":"crossref","first-page":"839","DOI":"10.32604\/iasc.2021.018572","article-title":"Extraction of opinion target using syntactic rules in Urdu text","volume":"29","author":"T A. Rana","year":"2021","journal-title":"Intell Automat Soft Comput"},{"key":"pone.0317562.ref020","first-page":"309","volume-title":"Aspect based sentiment analysis for Urdu. In: 2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","author":"N Ahmad","year":"2021"},{"issue":"1","key":"pone.0317562.ref021","first-page":"21","article-title":"Opinion within opinion: segmentation approach for Urdu sentiment analysis","volume":"15","author":"M Hassan","year":"2018","journal-title":"Int. Arab J. Inf. Technol"},{"issue":"3","key":"pone.0317562.ref022","doi-asserted-by":"crossref","first-page":"645","DOI":"10.3390\/sym15030645","article-title":"Contextually enriched meta-learning ensemble model for Urdu sentiment analysis","volume":"15","author":"K Ahmed","year":"2023","journal-title":"Symmetry"},{"key":"pone.0317562.ref023","unstructured":"Altaf A, Anwar MW, Jamal MH, Bajwa UI, Rani S.: Aspect-based sentiment analysis in Urdu language: resource creation and evaluation. Neural Comput Appl. 2014. 1\u201317."},{"key":"pone.0317562.ref024","doi-asserted-by":"crossref","unstructured":"Shabbir M, Majid M. Sentiment analysis from Urdu language-based text using deep learning techniques. In: Proceedings of 5th International Conference on Advancements in Computational Sciences. 2024. p. 1\u20135.","DOI":"10.1109\/ICACS60934.2024.10473232"},{"key":"pone.0317562.ref025","doi-asserted-by":"crossref","unstructured":"Ashraf MR, Jana Y, Umer Q, Jaffar MA, Chung S, Ramay WY. BERT based sentiment analysis for low-resourced languages: a case study of Urdu language. IEEE Access. 2023.","DOI":"10.1109\/ACCESS.2023.3322101"},{"issue":"27","key":"pone.0317562.ref026","doi-asserted-by":"crossref","first-page":"41813","DOI":"10.1007\/s11042-023-15216-0","article-title":"Exploiting linguistic features for effective sentence-level sentiment analysis in Urdu language","volume":"82","author":"A Altaf","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"pone.0317562.ref027","doi-asserted-by":"crossref","unstructured":"Zahid R, Idrees MO, Mujtaba H, Beg MO.: Roman urdu reviews dataset for aspect-based opinion mining. In: Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering. 2020. p. 138\u201343.","DOI":"10.1145\/3417113.3423377"},{"issue":"2","key":"pone.0317562.ref028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3474119","article-title":"An unsupervised approach for sentiment analysis on social media short text classification in Roman Urdu","volume":"21","author":"TA Rana","year":"2021","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"issue":"4","key":"pone.0317562.ref029","doi-asserted-by":"crossref","first-page":"102233","DOI":"10.1016\/j.ipm.2020.102233","article-title":"Deep sentiments in Roman Urdu text using Recurrent Convolutional Neural Network model","volume":"57","author":"Z Mahmood","year":"2020","journal-title":"Inf Process Manag"},{"key":"pone.0317562.ref030","doi-asserted-by":"crossref","first-page":"173186","DOI":"10.1109\/ACCESS.2020.3025823","article-title":"Aspect based sentiment analysis of ridesharing platform reviews for Kansei engineering","volume":"8","author":"S Ali","year":"2020","journal-title":"IEEE Access"},{"issue":"5","key":"pone.0317562.ref031","doi-asserted-by":"crossref","first-page":"2694","DOI":"10.3390\/app12052694","article-title":"Deep sentiment analysis using CNN-LSTM architecture of English and Roman Urdu text shared in social media","volume":"12","author":"L Khan","year":"2022","journal-title":"Appl Sci"},{"issue":"1","key":"pone.0317562.ref032","doi-asserted-by":"crossref","first-page":"2123094","DOI":"10.1080\/08839514.2022.2123094","article-title":"Deep sentiments analysis for roman Urdu dataset using faster recurrent convolutional neural network model","volume":"36","author":"AA Nagra","year":"2022","journal-title":"Appl Artif Intell"},{"issue":"7","key":"pone.0317562.ref033","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.3390\/app12073641","article-title":"Attention-based RU-BiLSTM sentiment analysis model for Roman Urdu","volume":"12","author":"BA Chandio","year":"2022","journal-title":"Appl Sci"},{"issue":"20","key":"pone.0317562.ref034","doi-asserted-by":"crossref","first-page":"10344","DOI":"10.3390\/app122010344","article-title":"Roman Urdu sentiment analysis using transfer learning","volume":"12","author":"D Li","year":"2022","journal-title":"Appl Sci"},{"issue":"03","key":"pone.0317562.ref035","first-page":"12","article-title":"Roman Urdu sentiment analysis of reviews on PSL anthems","volume":"6","author":"M Qureshi","year":"2022","journal-title":"Res J Comput Sci Inf Technol"},{"issue":"3","key":"pone.0317562.ref036","first-page":"503","article-title":"Convolutional neural network based sentiment analysis with tf-idf based vectorization","volume":"11","author":"B Kabra","year":"2023","journal-title":"J Integrat Sci Technol"},{"issue":"2","key":"pone.0317562.ref037","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2020.0110290","article-title":"Lexical variation and sentiment analysis of Roman Urdu sentences with deep neural networks","volume":"11","author":"MA Manzoor","year":"2020","journal-title":"IJACSA"},{"key":"pone.0317562.ref038","doi-asserted-by":"crossref","unstructured":"Hussain S.: Letter-to-sound conversion for Urdu text-to-speech system. In: International Conference on Computational Linguistics. 2004.","DOI":"10.3115\/1621804.1621823"},{"key":"pone.0317562.ref039","doi-asserted-by":"crossref","first-page":"91213","DOI":"10.1109\/ACCESS.2020.2994950","article-title":"Automatic detection of offensive language for Urdu and Roman Urdu","volume":"8","author":"MP Akhter","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0317562.ref040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3329709","article-title":"Sentiment analysis for a resource poor language\u2014Roman Urdu","volume":"19","author":"K Mehmood","year":"2019","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"pone.0317562.ref041","unstructured":"Ahmed T, Urooj S, Hussain S, Mustafa A, Parveen R, Adeeba F, et al. The CLE Urdu POS tagset. In: LREC 2014, Ninth International Conference on Language Resources and Evaluation. 2015. p. 2920\u20135."},{"issue":"3","key":"pone.0317562.ref042","doi-asserted-by":"crossref","first-page":"12397","DOI":"10.1111\/exsy.12397","article-title":"Creating sentiment lexicon for sentiment analysis in Urdu: the case of a resource\u2010poor language","volume":"36","author":"MZ Asghar","year":"2019","journal-title":"Exp Syst"},{"issue":"65","key":"pone.0317562.ref043","doi-asserted-by":"crossref","first-page":"59","DOI":"10.35950\/cbej.vi.7634","article-title":"Collocation in English and Arabic: a linguistic and cultural analysis","volume":"16","author":"ALBA Mustaf","year":"2022","journal-title":"CBEJ"},{"key":"pone.0317562.ref044","first-page":"22","article-title":"Using pointwise mutual information to identify implicit features in customer reviews.","volume-title":"International Conference on Computer Processing of Oriental Languages","author":"Q Su","year":"2006"},{"key":"pone.0317562.ref045","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"DM Blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"pone.0317562.ref046","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.eswa.2016.03.028","article-title":"Classification of sentiment reviews using n-gram machine learning approach","volume":"57","author":"A Tripathy","year":"2016","journal-title":"Exp Syst Appl"},{"key":"pone.0317562.ref047","doi-asserted-by":"crossref","unstructured":"Wallach HM, Murray I, Salakhutdinov R, Mimno D. Evaluation methods for topic models. In: Proceedings of the 26th Annual International Conference on Machine Learning. 2009.p. 1105\u201312.","DOI":"10.1145\/1553374.1553515"},{"key":"pone.0317562.ref048","unstructured":"Mimno D, Wallach H, Talley E, Leenders M, McCallum A. Optimizing semantic coherence in topic models. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. 2011. p. 262\u201372."},{"key":"pone.0317562.ref049","first-page":"19","article-title":"Semeval- 2016 task 5: aspect based sentiment analysis.","volume-title":"ProWorkshop on semantic evaluation (SemEval-2016)","author":"M Pontiki","year":"2016"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T17:42:53Z","timestamp":1749836573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317562"}},"subtitle":[],"editor":[{"given":"Bushra","family":"Zafar","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0317562","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,13]]}}}