{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:02:55Z","timestamp":1772823775114,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation (NSF)","award":["BSE-2214216"],"award-info":[{"award-number":["BSE-2214216"]}]},{"name":"National Science Foundation (NSF)","award":["HR001121C0165"],"award-info":[{"award-number":["HR001121C0165"]}]},{"name":"DARPA-INCAS","award":["BSE-2214216"],"award-info":[{"award-number":["BSE-2214216"]}]},{"name":"DARPA-INCAS","award":["HR001121C0165"],"award-info":[{"award-number":["HR001121C0165"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Studying public sentiment during crises is crucial for understanding how opinions and sentiments shift, resulting in polarized societies. We study Weibo, the most popular microblogging site in China, using posts made during the outbreak of the COVID-19 crisis. The study period includes the pre-COVID-19 stage, the outbreak stage, and the early stage of epidemic prevention. We use Llama 3 8B, a large language model, to analyze users\u2019 sentiments on the platform by classifying them into positive, negative, sarcastic, and neutral categories. Analyzing sentiment shifts on Weibo provides insights into how social events and government actions influence public opinion. This study contributes to understanding the dynamics of social sentiments during health crises, fulfilling a gap in sentiment analysis for Chinese platforms. By examining these dynamics, we aim to offer valuable perspectives on digital communication\u2019s role in shaping society\u2019s responses during unprecedented global challenges.<\/jats:p>","DOI":"10.3390\/e27030290","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T06:52:30Z","timestamp":1741675950000},"page":"290","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Using LLMs to Infer Non-Binary COVID-19 Sentiments of Chinese Microbloggers"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5868-7161","authenticated-orcid":false,"given":"Jerry Chongyi","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Network Science and Technology Center, Rensselaer Polytechnic Institute, Troy, NY 12180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5509-5277","authenticated-orcid":false,"given":"Mohammed Shahid","family":"Modi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Network Science and Technology Center, Rensselaer Polytechnic Institute, Troy, NY 12180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0307-6743","authenticated-orcid":false,"given":"Boleslaw K.","family":"Szymanski","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Network Science and Technology Center, Rensselaer Polytechnic Institute, Troy, NY 12180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"262","DOI":"10.3934\/publichealth.2022018","article-title":"The impact of misinformation on the COVID-19 pandemic","volume":"9","author":"Caceres","year":"2022","journal-title":"AIMS Public Health"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wu, Q., Sano, Y., Takayasu, H., and Takayasu, M. (2022). Classification of endogenous and exogenous bursts in collective emotions based on Weibo comments during COVID-19. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-07067-w"},{"key":"ref_3","unstructured":"AI@Meta (2024, December 29). Llama 3 Model Card. Available online: https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md."},{"key":"ref_4","unstructured":"LlamaTeam (2024). The Llama 3 Herd of Models. arXiv."},{"key":"ref_5","unstructured":"Rosen, G. (2024, December 06). How We\u2019re Tackling Misinformation Across Our Apps. Available online: https:\/\/about.fb.com\/news\/2021\/03\/how-were-tackling-misinformation-across-our-apps\/."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhao, A., and Hu, H.L. (2023). Rule social media with users: Unveiling Strategical Governance and User Dynamics in Weibo\u2019s Community-driven Content Moderation System. SocArXiv.","DOI":"10.31235\/osf.io\/da8fz"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.tele.2017.10.006","article-title":"Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis","volume":"35","author":"Ayvaz","year":"2018","journal-title":"Telemat Inf."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Backfried, G., and Shalunts, G. (2016, January 26\u201328). Sentiment Analysis of Media in German on the Refugee Crisis in Europe. Proceedings of the Information Systems for Crisis Response and Management in Mediterranean Countries, Madrid, Spain.","DOI":"10.1007\/978-3-319-47093-1_20"},{"key":"ref_9","first-page":"1","article-title":"Applying sentiment analytics to examine social media crises: A case study of United Airline\u2019s crisis in 2017","volume":"56","author":"Tian","year":"2022","journal-title":"Data Technol. Appl."},{"key":"ref_10","first-page":"1","article-title":"Shifting sentiments: Analyzing public reaction to COVID-19 containment policies in Wuhan and Shanghai through Weibo data","volume":"11","author":"Liu","year":"2024","journal-title":"Humanit. Soc. Sci. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1057\/s41599-024-02969-8","article-title":"Pathos or logos? How governance legitimacy perception influences individual privacy trade-offs during COVID-19 pandemic","volume":"11","author":"Meng","year":"2024","journal-title":"Humanit. Soc. Sci. Commun."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1177\/17427665221100596","article-title":"Avoiding online censorship through \u2018fatty\u2019 memes: How Chinese social media users talk about North Korea","volume":"18","author":"Zhang","year":"2022","journal-title":"Glob. Media Commun."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101712","DOI":"10.1016\/j.tele.2021.101712","article-title":"Exploring public perceptions of the COVID-19 vaccine online from a cultural perspective: Semantic network analysis of two social media platforms in the United States and China","volume":"65","author":"Luo","year":"2021","journal-title":"Telemat Inf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Augustyniak, L., Kajdanowicz, T., Szyma\u0144ski, P., Tulig\u0142owicz, W., Kazienko, P., Alhajj, R., and Szymanski, B. (2014, January 17\u201320). Simpler is better? Lexicon-based ensemble sentiment classification beats supervised methods. Proceedings of the 2014 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014), Beijing, China.","DOI":"10.1109\/ASONAM.2014.6921696"},{"key":"ref_15","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 International Conference on Language Resources and Evaluation, LREC 2010, Valletta, Malta."},{"key":"ref_16","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_17","first-page":"1995","article-title":"Analysis of the evolution of advanced transformer-based language models: Experiments on opinion mining","volume":"12","author":"Zekaoui","year":"2023","journal-title":"IAES Int. J. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ghatora, P.S., Hosseini, S.E., Pervez, S., Iqbal, M.J., and Shaukat, N. (2024). Sentiment Analysis of Product Reviews Using Machine Learning and Pre-Trained LLM. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8120199"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Heraldi, F.D., and Ruskanda, Z. (2024, January 28\u201330). Effective Intended Sarcasm Detection Using Fine-tuned Llama 2 Large Language Models. Proceedings of the 2024 11th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), Singapore.","DOI":"10.1109\/ICAICTA63815.2024.10763281"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ihnaini, B., Sun, W., Cai, Y., Xu, Z., and Sangi, R. (2024, January 24\u201327). Sentiment Analysis of Song Dynasty Classical Poetry Using Fine-Tuned Large Language Models: A Study with LLMs. Proceedings of the 2024 7th International Conference on Artificial Intelligence and Big Data (ICAIBD), Chengdu, China.","DOI":"10.1109\/ICAIBD62003.2024.10604440"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Suhaimin, M.S.M., Hijazi, M.H.A., Alfred, R., and Coenen, F. (2017, January 17\u201318). Natural language processing based features for sarcasm detection: An investigation using bilingual social media texts. Proceedings of the 2017 8th International Conference on Information Technology (ICIT), Amman, Jordan.","DOI":"10.1109\/ICITECH.2017.8079931"},{"key":"ref_22","first-page":"1175","article-title":"Modified framework for sarcasm detection and classification in sentiment analysis","volume":"13","author":"Suhaimin","year":"2019","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1080\/01638539509544916","article-title":"On irony and negation","volume":"19","author":"Giora","year":"1995","journal-title":"Discourse Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.cortex.2019.01.025","article-title":"What is the difference between irony and sarcasm? An fMRI study","volume":"115","author":"Filik","year":"2019","journal-title":"Cortex"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1515\/humor-2012-0019","article-title":"Satire and definition","volume":"25","author":"Condren","year":"2012","journal-title":"Humor"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6287559","DOI":"10.1155\/2022\/6287559","article-title":"Evolution and Evaluation: Sarcasm Analysis for Twitter Data Using Sentiment Analysis","volume":"2022","author":"Bhakuni","year":"2022","journal-title":"J. Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"76","DOI":"10.54117\/gjpas.v2i1.72","article-title":"Sentiment analysis of sarcasm detection in social media","volume":"2","author":"Alaramma","year":"2023","journal-title":"Gadau J. Pure Allied Sci."},{"key":"ref_28","unstructured":"Zhai, Y. (2020). Weibo COVID Dataset. arXiv."},{"key":"ref_29","first-page":"18794","article-title":"CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations","volume":"Volume 36","author":"Oh","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_30","unstructured":"OpenAI (2025, February 09). Hello GPT-4o. Available online: https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"ref_31","unstructured":"West, R., and Horvitz, E. (February, January 27). Reverse-Engineering Satire, or \u201cPaper on Computational Humor Accepted despite Making Serious Advances\u201d. Proceedings of the AAAI Conference on Artifical Intelligence, Honolulu, HI, USA."},{"key":"ref_32","unstructured":"Liu, Y., Zhu, X., Shen, Z., Liu, Y., Li, M., Chen, Y., John, B., Ma, Z., Hu, T., and Li, Z. (2025). Do Large Language Models Possess Sensitive to Sentiment?. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Adali, S., Escriva, R., Goldberg, M.K., Hayvanovych, M., Magdon-Ismail, M., Szymanski, B.K., Wallace, W.A., and Williams, G. (2010, January 23\u201326). Measuring behavioral trust in social networks. Proceedings of the 2010 IEEE international conference on intelligence and security informatics, Vancouver, BC, Canada.","DOI":"10.1109\/ISI.2010.5484757"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Kulisiewicz, M., Kazienko, P., Szymanski, B.K., and Michalski, R. (2018). Entropy measures of human communication dynamics. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-32571-3"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Flamino, J., Gong, B., Buchanan, F., and Szymanski, B.K. (2021). Characterizing topics in social Media using dynamics of conversation. Entropy, 23.","DOI":"10.3390\/e23121642"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Horne, B., and Adali, S. (2017, January 15\u201318). This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news. Proceedings of the International AAAI Conference on Web and Social Media, Montreal, QC, Canada.","DOI":"10.1609\/icwsm.v11i1.14976"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/3\/290\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:50:27Z","timestamp":1760028627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/3\/290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["e27030290"],"URL":"https:\/\/doi.org\/10.3390\/e27030290","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]}}}