{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:30:19Z","timestamp":1776717019147,"version":"3.51.2"},"reference-count":46,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"\u201cFrance 2030\u201d, introduced by the French Government and implemented by ANR","award":["ANR-21-EXES-0007"],"award-info":[{"award-number":["ANR-21-EXES-0007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>With the rapid growth in social network comments, the need for more effective methods to classify their polarity\u2014negative, neutral, or positive\u2014has become essential. Sentiment analysis, powered by natural language processing, has evolved significantly with the adoption of advanced deep learning techniques. Long Short-Term Memory networks capture long-range dependencies in text, while transformers, with their attention mechanisms, excel at preserving contextual meaning and handling high-dimensional, semantically complex data. This study compares the performance of sentiment analysis models based on LSTM and BERT architectures using key evaluation metrics. The dataset consists of business reviews from the Yelp Open Dataset. We tested LSTM-based methods against BERT and its variants\u2014RoBERTa, BERTweet, and DistilBERT\u2014leveraging popular pipelines from the Hugging Face Hub. A class-by-class performance analysis is presented, revealing that more complex BERT-based models do not always guarantee superior results in the classification of Yelp reviews. Additionally, the use of bidirectionality in LSTMs does not necessarily lead to better performance. However, across a diversity of test sets, transformer models outperform traditional RNN-based models, as their generalization capability is greater than that of a simple LSTM model.<\/jats:p>","DOI":"10.3390\/bdcc9050140","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T07:44:57Z","timestamp":1747813497000},"page":"140","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Polarity of Yelp Reviews: A BERT\u2013LSTM Comparative Study"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-1226","authenticated-orcid":false,"given":"Rachid","family":"Belaroussi","sequence":"first","affiliation":[{"name":"COSYS-GRETTIA, University Gustave Eiffel, F-77447 Marne-la-Vall\u00e9e, France"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2490-1585","authenticated-orcid":false,"given":"Si\u00e9 Cyriac","family":"Noufe","sequence":"additional","affiliation":[{"name":"COSYS-GRETTIA, University Gustave Eiffel, F-77447 Marne-la-Vall\u00e9e, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5853-1531","authenticated-orcid":false,"given":"Francis","family":"Dupin","sequence":"additional","affiliation":[{"name":"COSYS-GRETTIA, University Gustave Eiffel, F-77447 Marne-la-Vall\u00e9e, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1833-4669","authenticated-orcid":false,"given":"Pierre-Olivier","family":"Vandanjon","sequence":"additional","affiliation":[{"name":"AME-SPLOTT, University Gustave Eiffel, All. des Ponts et Chauss\u00e9es, F-44340 Bouguenais, France"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","article-title":"A survey on sentiment analysis methods, applications, and challenges","volume":"55","author":"Wankhade","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107134","DOI":"10.1016\/j.knosys.2021.107134","article-title":"A comprehensive survey on sentiment analysis: Approaches, challenges and trends","volume":"226","author":"Birjali","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mohammad, S.M. (2021). Sentiment analysis: Automatically detecting valence, emotions, and other affectual states from text. Emotion Measurement, Woodhead Publishing.","DOI":"10.1016\/B978-0-12-821124-3.00011-9"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s40537-015-0015-2","article-title":"Sentiment analysis using product review data","volume":"2","author":"Fang","year":"2015","journal-title":"J. Big Data"},{"key":"ref_5","doi-asserted-by":"crossref","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. Pract. Exp."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Pagolu, V.S., Reddy, K.N., Panda, G., and Majhi, B. (2016, January 3\u20135). Sentiment analysis of Twitter data for predicting stock market movements. Proceedings of the 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), Paralakhemundi, India.","DOI":"10.1109\/SCOPES.2016.7955659"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Valencia, F., G\u00f3mez-Espinosa, A., and Vald\u00e9s-Aguirre, B. (2019). Price movement prediction of cryptocurrencies using sentiment analysis and machine learning. Entropy, 21.","DOI":"10.3390\/e21060589"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Roumeliotis, K.I., Tselikas, N.D., and Nasiopoulos, D.K. (2024). LLMs and NLP Models in Cryptocurrency Sentiment Analysis: A Comparative Classification Study. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8060063"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e22624","DOI":"10.2196\/22624","article-title":"Topics, trends, and sentiments of tweets about the COVID-19 pandemic: Temporal infoveillance study","volume":"22","author":"Chandrasekaran","year":"2020","journal-title":"J. Med. Internet Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e21978","DOI":"10.2196\/21978","article-title":"Public perception of the COVID-19 pandemic on Twitter: Sentiment analysis and topic modeling study","volume":"6","author":"Skunkan","year":"2020","journal-title":"JMIR Public Health Surveill."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Matalon, Y., Magdaci, O., Almozlino, A., and Yamin, D. (2021). Using sentiment analysis to predict opinion inversion in Tweets of political communication. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-86510-w"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1177\/1461444813480466","article-title":"Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens\u2019 political preferences with an application to Italy and France","volume":"16","author":"Ceron","year":"2014","journal-title":"New Media Soc."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hutto, C., and Gilbert, E. (2014, January 1\u20134). Vader: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the International AAAI Conference on Web and Social Media, Ann Arbor, MI, USA.","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"ref_14","unstructured":"Baccianella, S., Esuli, A., and Sebastiani, F. (2010, January 17\u201323). Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910), Valletta, Malta. Available online: http:\/\/www.lrec-conf.org\/proceedings\/lrec2010\/pdf\/769_Paper.pdf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e1253","DOI":"10.1002\/widm.1253","article-title":"Deep learning for sentiment analysis: A survey","volume":"8","author":"Zhang","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Phys. D Nonlinear Phenom."},{"key":"ref_17","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_18","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1109\/TAFFC.2020.3038167","article-title":"Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research","volume":"14","author":"Poria","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Barbieri, F., Camacho-Collados, J., Neves, L., and Espinosa-Anke, L. (2020). Tweeteval: Unified benchmark and comparative evaluation for tweet classification. arXiv.","DOI":"10.18653\/v1\/2020.findings-emnlp.148"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Areshey, A., and Mathkour, H. (2023). Transfer Learning for Sentiment Classification Using Bidirectional Encoder Representations from Transformers (BERT) Model. Sensors, 23.","DOI":"10.3390\/s23115232"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mutinda, J., Mwangi, W., and Okeyo, G. (2023). Sentiment Analysis of Text Reviews Using Lexicon-Enhanced Bert Embedding (LeBERT) Model with Convolutional Neural Network. Appl. Sci., 13.","DOI":"10.3390\/app13031445"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Nguyen, D.Q., Vu, T., and Nguyen, A.T. (2020, January 16\u201320). BERTweet: A pre-trained language model for English Tweets. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online.","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"ref_24","unstructured":"Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv."},{"key":"ref_25","unstructured":"P\u00e9rez, J.M., Giudici, J.C., and Luque, F. (2021). pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Loureiro, D., Barbieri, F., Neves, L., Espinosa Anke, L., and Camacho-collados, J. (2022, January 22\u201327). TimeLMs: Diachronic Language Models from Twitter. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-demo.25"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Plank, B., S\u00f8gaard, A., and Goldberg, Y. (2016). Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss. arXiv.","DOI":"10.18653\/v1\/P16-2067"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Basiri, M.E., Chegeni, R.S., Karimvand, A.N., and Nemati, S. (2020, January 22\u201323). Bidirectional LSTM Deep Model for Online Doctor Reviews Polarity Detection. Proceedings of the 2020 6th International Conference on Web Research (ICWR), Teheran, Iran.","DOI":"10.1109\/ICWR49608.2020.9122289"},{"key":"ref_29","unstructured":"Wang, X., Liu, Y., Sun, C.J., Wang, B., and Wang, X. (, January July). Predicting polarities of tweets by composing word embeddings with long short-term memory. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kapali, N., Tuhin, T., Pramanik, A., Rahman, M.S., and Noori, S.R.H. (2022, January 3\u20135). Sentiment Analysis of Facebook and YouTube Bengali Comments Using LSTM and Bi-LSTM. Proceedings of the 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), Virtual.","DOI":"10.1109\/ICCCNT54827.2022.9984395"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"58","DOI":"10.24018\/ejece.2023.7.6.583","article-title":"Evaluation of Machine Learning Approach for Sentiment Analysis using Yelp Dataset","volume":"7","author":"Sadikin","year":"2023","journal-title":"Eur. J. Electr. Eng. Comput. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chandra, R., Sonawane, J., and Lande, J. (2024). An Analysis of Vaccine-Related Sentiments on Twitter (X) from Development to Deployment of COVID-19 Vaccines. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8120186"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"128494","DOI":"10.1109\/ACCESS.2021.3111035","article-title":"Biden vs Trump: Modeling US General Elections Using BERT Language Model","volume":"9","author":"Chandra","year":"2021","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Bello, A., Ng, S.C., and Leung, M.F. (2023). A BERT Framework to Sentiment Analysis of Tweets. Sensors, 23.","DOI":"10.3390\/s23010506"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1177\/1094428120971683","article-title":"Text Preprocessing for Text Mining in Organizational Research: Review and Recommendations","volume":"25","author":"Hickman","year":"2022","journal-title":"Organ. Res. Methods"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_37","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C.D., Ng, A., and Potts, C. (2013, January 18\u201321). Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA. Available online: https:\/\/nlp.stanford.edu\/~socherr\/EMNLP2013_RNTN.pdf.","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Camacho-collados, J., Rezaee, K., Riahi, T., Ushio, A., Loureiro, D., Antypas, D., Boisson, J., Espinosa Anke, L., Liu, F., and Mart\u00ednez C\u00e1mara, E. (2022, January 7\u201311). TweetNLP: Cutting-Edge Natural Language Processing for Social Media. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-demos.5"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Iqbal, A., Amin, R., Iqbal, J., Alroobaea, R., Binmahfoudh, A., and Hussain, M. (2022). Sentiment Analysis of Consumer Reviews Using Deep Learning. Sustainability, 14.","DOI":"10.3390\/su141710844"},{"key":"ref_41","unstructured":"Hou, Y., Li, J., He, Z., Yan, A., Chen, X., and McAuley, J. (2024). Bridging Language and Items for Retrieval and Recommendation. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Rosenthal, S., Farra, N., and Nakov, P. (2019). SemEval-2017 task 4: Sentiment analysis in Twitter. arXiv.","DOI":"10.18653\/v1\/S17-2088"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.57041\/6t2gfw23","article-title":"Comparative Analysis of Logistic Regression, LSTM, and Bi-LSTM Models for Sentiment Analysis on IMDB Movie Reviews","volume":"2","author":"Hussain","year":"2024","journal-title":"J. Artif. Intell. Comput."},{"key":"ref_44","unstructured":"Warner, B., Chaffin, A., Clavi\u00e9, B., Weller, O., Hallstr\u00f6m, O., Taghadouini, S., Gallagher, A., Biswas, R., Ladhak, F., and Aarsen, T. (2025, May 02). Finally, a Replacement for BERT: Introducing ModernBERT. Available online: https:\/\/huggingface.co\/blog\/modernbert."},{"key":"ref_45","unstructured":"BehnamGhader, P., Adlakha, V., Mosbach, M., Bahdanau, D., Chapados, N., and Reddy, S. (2024). LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s40547-024-00143-4","article-title":"Sentiment analysis in the age of generative AI","volume":"11","author":"Krugmann","year":"2024","journal-title":"Cust. Needs Solut."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/5\/140\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:36:31Z","timestamp":1760031391000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/5\/140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":46,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["bdcc9050140"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9050140","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,21]]}}}