{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:10:04Z","timestamp":1780506604327,"version":"3.54.1"},"reference-count":64,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015283","name":"Bloomberg Philanthropies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015283","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Sentiment analysis has become a crucial area of research in natural language processing in recent years. The study aims to compare the performance of various sentiment analysis techniques, including lexicon-based, machine learning, Bi-LSTM, BERT, and GPT-3 approaches, using two commonly used datasets, IMDB reviews and Sentiment140. The objective is to identify the best-performing technique for an exemplar dataset, tweets associated with the WHO Framework Convention on Tobacco Control Ninth Conference of the Parties in 2021 (COP9).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A two-stage evaluation was conducted. In the first stage, various techniques were compared on standard sentiment analysis datasets using standard evaluation metrics such as accuracy, F1-score, and precision. In the second stage, the best-performing techniques from the first stage were applied to partially annotated COP9 conference-related tweets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the first stage, BERT achieved the highest F1-scores (0.9380 for IMDB and 0.8114 for Sentiment 140), followed by GPT-3 (0.9119 and 0.7913) and Bi-LSTM (0.8971 and 0.7778). In the second stage, GPT-3 performed the best for sentiment analysis on partially annotated COP9 conference-related tweets, with an F1-score of 0.8812.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The study demonstrates the effectiveness of pre-trained models like BERT and GPT-3 for sentiment analysis tasks, outperforming traditional techniques on standard datasets. Moreover, the better performance of GPT-3 on the partially annotated COP9 tweets highlights its ability to generalize well to domain-specific data with limited annotations. This provides researchers and practitioners with a viable option of using pre-trained models for sentiment analysis in scenarios with limited or no annotated data across different domains.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdata.2024.1357926","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T04:43:40Z","timestamp":1710909820000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques"],"prefix":"10.3389","volume":"7","author":[{"given":"Sherif","family":"Elmitwalli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Mehegan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,3,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5789","DOI":"10.1007\/s10462-021-09958-2","article-title":"Transformer models for text-based emotion detection: a review of BERT-based approaches","volume":"54","author":"Acheampong","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"B2","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1057\/s41270-021-00109-8","article-title":"Bert: a sentiment analysis odyssey","volume":"9","author":"Alaparthi","year":"2021","journal-title":"J. Market. Analyt."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1109\/ASEW52652.2021.00053","article-title":"\u201cLearning sentiment analysis for accessibility user reviews,\u201d","author":"Aljedaani","year":"2021","journal-title":"2021 36th IEEE\/ACM International Conference on Automated Software Engineering Workshops (ASEW)."},{"key":"B4","doi-asserted-by":"publisher","first-page":"102132","DOI":"10.1016\/j.ijinfomgt.2020.102132","article-title":"A comparative assessment of sentiment analysis and star ratings for consumer reviews","volume":"54","author":"Al-Natour","year":"2020","journal-title":"Int. J. Inf. Manag"},{"key":"B5","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1080\/1206212X.2019.1658054","article-title":"Multimodal sentiment analysis using Relieff feature selection and random forest classifier","volume":"43","author":"Angadi","year":"2021","journal-title":"Int. J. Comput. Applic."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11063-022-11111-1","article-title":"Improving the polarity of text through word2vec embedding for primary classical arabic sentiment analysis","volume":"23","author":"Aoumeur","year":"2023","journal-title":"Neural Proc. Lett."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.heliyon.2019.e02504","article-title":"Statistical-based system combination approach to gain advantages over different machine translation systems","volume":"5","author":"Banik","year":"2019","journal-title":"Heliyon."},{"key":"B8","doi-asserted-by":"publisher","first-page":"506","DOI":"10.3390\/s23010506","article-title":"A BERT framework to sentiment analysis of tweets","volume":"23","author":"Bello","year":"2023","journal-title":"Sensors."},{"key":"B9","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1136\/tobaccocontrol-2021-056545","article-title":"Where next for the WHO framework convention on tobacco control?","volume":"31","author":"Bialous","year":"2022","journal-title":"Tobacco Control."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1016\/j.surg.2020.09.020","article-title":"Machine learning analyses of automated performance metrics during granular sub-stitch phases predict surgeon experience","volume":"169","author":"Chen","year":"2021","journal-title":"Surgery."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e0298298","DOI":"10.1371\/journal.pone.0298298","article-title":"Topic prediction for tobacco control based on COP9 tweets using machine learning techniques","volume":"19","author":"Elmitwalli","year":"2024","journal-title":"PLoS ONE."},{"key":"B12","doi-asserted-by":"publisher","first-page":"102438","DOI":"10.1016\/j.ipm.2020.102438","article-title":"A comparative study of effective approaches for Arabic sentiment analysis","volume":"58","author":"Farha","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"B13","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1016\/j.procs.2019.11.181","article-title":"Sentiment analysis of social media Twitter with case of Anti-LGBT campaign in Indonesia using Na\u00efve Bayes, decision tree, random forest algorithm","volume":"161","author":"Fitri","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-981-33-6919-1_10","article-title":"\u201cTwitter data sentiment analysis using naive Bayes classifier and generation of heat map for analyzing intensity geographically,\u201d","author":"Gautam","year":"2021","journal-title":"Advances in Applications of Data-Driven Computing"},{"key":"B15","doi-asserted-by":"publisher","first-page":"374","DOI":"10.3390\/info12090374","article-title":"A tweet sentiment classification approach using a hybrid stacked ensemble technique","volume":"12","author":"Gaye","year":"2021","journal-title":"Information."},{"key":"B16","article-title":"In-context autoencoder for context compression in a large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint arXiv:2307.06945"},{"key":"B17","first-page":"2009","article-title":"Twitter sentiment classification using distant supervision CS224N project report","volume":"1","author":"Go","year":"2009","journal-title":"Stanford"},{"key":"B18","doi-asserted-by":"publisher","first-page":"101164","DOI":"10.1016\/j.mex.2020.101164","article-title":"Modeling influence and community in social media data using the digital methods initiative-twitter capture and analysis toolkit (DMI-TCAT) and gephi","volume":"7","author":"Groshek","year":"2020","journal-title":"MethodsX"},{"key":"B19","doi-asserted-by":"publisher","first-page":"107907","DOI":"10.1016\/j.engappai.2024.107907","article-title":"AGCVT-prompt for sentiment classification: Automatically generating chain of thought and verbalizer in prompt learning","volume":"132","author":"Gu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B20","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.matpr.2021.04.364","article-title":"Comparative analysis of machine learning-based classification models using sentiment classification of tweets related to covid-19 pandemic","volume":"51","author":"Gulati","year":"2022","journal-title":"Mater. Today."},{"key":"B21","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1080\/02533839.2021.1933598","article-title":"SentiXGboost: Enhanced sentiment analysis in social media posts with ensemble XGBoost classifier","volume":"44","author":"Hama Aziz","year":"2021","journal-title":"J. Chin. Inst. Eng."},{"key":"B22","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1609\/icwsm.v8i1.14550","article-title":"\u201cVader: a parsimonious rule-based model for sentiment analysis of social media text,\u201d","author":"Hutto","year":"2014","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media"},{"key":"B23","doi-asserted-by":"publisher","first-page":"100413","DOI":"10.1016\/j.cosrev.2021.100413","article-title":"A systematic literature review on machine learning applications for consumer sentiment analysis using online reviews","volume":"41","author":"Jain","year":"2021","journal-title":"Comput. Sci. Rev."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e0220976","DOI":"10.1371\/journal.pone.0220976","article-title":"Word2vec convolutional neural networks for classification of news articles and tweets","volume":"14","author":"Jang","year":"2019","journal-title":"PLoS ONE"},{"key":"B25","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1016\/j.procs.2021.12.187","article-title":"Sentiment analysis of Twitter data related to Rinca Island development using doc2vec and SVM and logistic regression as classifier","volume":"197","author":"Jaya Hidayat","year":"2022","journal-title":"Proc. Comput. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"100048","DOI":"10.2139\/ssrn.4593895","article-title":"A survey of GPT-3 family large language models including ChatGPT and GPT-4","volume":"19","author":"Kalyan","year":"2023","journal-title":"Natural Lang. Proc. J."},{"key":"B27","doi-asserted-by":"publisher","first-page":"5436","DOI":"10.1038\/s41598-022-09381-9","article-title":"Multi-class sentiment analysis of urdu text using multilingual BERT","volume":"12","author":"Khan","year":"2022","journal-title":"Sci. Rep."},{"key":"B28","doi-asserted-by":"publisher","first-page":"107056","DOI":"10.1109\/ACCESS.2022.3212367","article-title":"Sentiment analysis using pre-trained language model with no fine-tuning and less resource","volume":"10","author":"Kit","year":"2022","journal-title":"IEEE Access."},{"key":"B29","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s40745-021-00344-x","article-title":"A comprehensive comparative study of Artificial Neural Network (ANN) and support vector machines (SVM) on stock forecasting","volume":"10","author":"Kurani","year":"2021","journal-title":"Ann. Data Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1016\/j.engappai.2019.07.010","article-title":"A reproducible survey on word embeddings and ontology-based methods for word similarity: Linear combinations outperform the state of the art","volume":"85","author":"Lastra-D\u00edaz","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B31","doi-asserted-by":"publisher","first-page":"106755","DOI":"10.1016\/j.asoc.2020.106755","article-title":"Applying sentiment analysis to automatically classify consumer comments concerning marketing 4Cs aspects","volume":"97","author":"Lin","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"B32","doi-asserted-by":"publisher","first-page":"101014","DOI":"10.1016\/j.seta.2021.101014","article-title":"Sentiment analysis of low-carbon travel app user comments based on Deep Learning","volume":"44","author":"Lin","year":"2021","journal-title":"Sustain. Energy Technol. Assess."},{"key":"B33","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1109\/TASLP.2023.3240661","article-title":"\u201cVariational latent-state GPT for semi-supervised task-oriented Dialog Systems,\u201d","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, Language Processing"},{"key":"B34","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/978-981-19-6581-4_21","article-title":"\u201cTwitter sentiment analysis using enhanced bert,\u201d","volume-title":"InIntelligent Systems and Applications: Select Proceedings of ICISA 2022","author":"Mann","year":"2023"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-021-01742-0","article-title":"Comparing machine learning algorithms for predicting COVID-19 mortality","volume":"22","author":"Moulaei","year":"2022","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B36","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1111\/add.15628","article-title":"E-cigarettes versus nicotine replacement treatment as harm reduction interventions for smokers who find quitting difficult: Randomized controlled trial","volume":"117","author":"Myers Smith","year":"2021","journal-title":"Addiction"},{"key":"B37","doi-asserted-by":"publisher","first-page":"10602","DOI":"10.1007\/s10489-022-04052-8","article-title":"Transformer models used for text-based question answering systems","volume":"53","author":"Nassiri","year":"2023","journal-title":"Appl. Intell."},{"key":"B38","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1136\/bjophthalmol-2022-321141","article-title":"New meaning for NLP: The trials and tribulations of natural language processing with GPT-3 in ophthalmology","volume":"106","author":"Nath","year":"2022","journal-title":"Br. J. Ophthalmol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"101785","DOI":"10.1016\/j.is.2021.101785","article-title":"Multi-label arabic text classification in online social networks","volume":"100","author":"Omar","year":"2021","journal-title":"Inf. Syst."},{"key":"B40","doi-asserted-by":"publisher","first-page":"9779","DOI":"10.1038\/s41598-022-13153-w","article-title":"Character gated recurrent neural networks for Arabic sentiment analysis","volume":"12","author":"Omara","year":"2022","journal-title":"Sci. Rep."},{"key":"B41","doi-asserted-by":"publisher","first-page":"e5909","DOI":"10.1002\/cpe.5909","article-title":"Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks","volume":"33","author":"Onan","year":"2021","journal-title":"Concurr. Comput."},{"key":"B42","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/978-981-16-4284-5_18","article-title":"\u201cA comparative study on sentiment analysis influencing word embedding using SVM and KNN,\u201d","volume-title":"Cyber Intelligence and Information Retrieval: Proceedings of CIIR 2021","author":"Paul","year":"2022"},{"key":"B43","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1007\/978-981-19-5037-7_40","article-title":"\u201cComparison of BERT-Base and GPT-3 for marathi text classification,\u201d","volume-title":"Futuristic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021","author":"Pawar","year":"2022"},{"key":"B44","article-title":"The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, web data only","author":"Penedo","year":"2023","journal-title":"arXiv preprint arXiv:2306.01116"},{"key":"B45","doi-asserted-by":"publisher","first-page":"117581","DOI":"10.1016\/j.eswa.2022.117581","article-title":"MBiLSTMGloVe: embedding GloVe knowledge into the corpus using multi-layer BiLSTM deep learning model for social media sentiment analysis","volume":"203","author":"Pimpalkar","year":"2022","journal-title":"Expert. Syst. Appl."},{"key":"B46","doi-asserted-by":"publisher","first-page":"115119","DOI":"10.1016\/j.eswa.2021.115119","article-title":"Multilingual evaluation of pre-processing for BERT-based sentiment analysis of tweets","volume":"181","author":"Pota","year":"2021","journal-title":"Expert. Syst. Appl."},{"key":"B47","doi-asserted-by":"publisher","first-page":"119862","DOI":"10.1016\/j.eswa.2023.119862","article-title":"A review on sentiment analysis from social media platforms","volume":"223","author":"Rodr\u00edguez-Ib\u00e1nez","year":"2023","journal-title":"Expert. Syst. Appl."},{"key":"B48","doi-asserted-by":"publisher","first-page":"100056","DOI":"10.1016\/j.nlp.2024.100056","article-title":"LLMs in e-commerce: a comparative analysis of GPT and LLaMA models in product review evaluation","volume":"19","author":"Roumeliotis","year":"2024","journal-title":"Nat. Lang. Proc. J."},{"key":"B49","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s12652-018-0862-8","article-title":"Sentiment analysis: a review and comparative analysis over social media","volume":"11","author":"Singh","year":"2020","journal-title":"J. Ambient Intell. Hum. Comput."},{"key":"B50","doi-asserted-by":"publisher","first-page":"4550","DOI":"10.3390\/app13074550","article-title":"A survey of sentiment analysis: approaches, datasets, future research","volume":"13","author":"Tan","year":"2023","journal-title":"Appl. Sci."},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-023-10472-w","article-title":"A systematic review of social network sentiment analysis with comparative study of ensemble-based techniques","volume":"12","author":"Tiwari","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM.2016.7752387","article-title":"\u201cMovie review analysis: emotion analysis of IMDB movie reviews,\u201d","author":"Topal","year":"2016","journal-title":"2016 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)."},{"key":"B53","doi-asserted-by":"publisher","first-page":"5569","DOI":"10.1007\/s11042-022-13459-x","article-title":"Impact of convolutional neural network and FastText embedding on text classification","volume":"82","author":"Umer","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"B54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3589131","article-title":"\u201cVietnamese sentiment analysis: an overview and comparative study of fine-tuning pretrained language models,\u201d","author":"Van Thin","year":"2023","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"B55","article-title":"Attention is all you need. Advances in Neural Information Processing Systems (Vol. 30)","author":"Vaswani","year":"2017","journal-title":"arXiv [Preprint]"},{"key":"B56","doi-asserted-by":"publisher","first-page":"6155","DOI":"10.1007\/s10462-020-09845-2","article-title":"Sentiment analysis with deep neural networks: comparative study and performance assessment","volume":"53","author":"Wadawadagi","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"B57","doi-asserted-by":"publisher","first-page":"103609","DOI":"10.1016\/j.ipm.2023.103609","article-title":"Emotion-cognitive reasoning integrated BERT for sentiment analysis of online public opinions on emergencies","volume":"61","author":"Wan","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"B58","doi-asserted-by":"publisher","first-page":"138162","DOI":"10.1109\/ACCESS.2020.3012595","article-title":"COVID-19 sensing: negative sentiment analysis on social media in china via BERT model","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"B59","doi-asserted-by":"publisher","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","article-title":"A survey on sentiment analysis methods, applications, challenges","volume":"55","author":"Wankhade","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"B60","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.1007\/s10639-019-10073-7","article-title":"Opinion mining technique for developing student feedback analysis system using lexicon-based approach (OMFeedback)","volume":"25","author":"Wook","year":"2019","journal-title":"Educ. Inf. Technol."},{"key":"B61","doi-asserted-by":"publisher","first-page":"307","DOI":"10.3390\/healthcare8030307","article-title":"Sentiment Analysis Methods for HPV vaccines related tweets based on transfer learning","volume":"8","author":"Zhang","year":"2020","journal-title":"Healthcare."},{"key":"B62","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1007\/s10489-019-01441-4","article-title":"A quantum-inspired sentiment representation model for Twitter sentiment analysis","volume":"49","author":"Zhang","year":"2019","journal-title":"Appl. Intell."},{"key":"B63","doi-asserted-by":"publisher","first-page":"107220","DOI":"10.1016\/j.knosys.2021.107220","article-title":"Knowledge-enabled Bert for aspect-based sentiment analysis","volume":"227","author":"Zhao","year":"2021","journal-title":"Knowl Based Syst."},{"key":"B64","doi-asserted-by":"publisher","first-page":"15561","DOI":"10.1109\/ACCESS.2021.3052937","article-title":"Combination of convolutional neural network and gated recurrent unit for aspect-based sentiment analysis","volume":"9","author":"Zhao","year":"2021","journal-title":"IEEE Access."}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1357926\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T04:43:51Z","timestamp":1710909831000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1357926\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,20]]},"references-count":64,"alternative-id":["10.3389\/fdata.2024.1357926"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2024.1357926","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,20]]},"article-number":"1357926"}}