{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T01:52:31Z","timestamp":1790128351497,"version":"4.0.1"},"reference-count":94,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>While the COVID-19 pandemic has induced massive discussion of available medications on social media, traditional studies focused only on limited aspects, such as public opinions, and endured reporting biases, inefficiency, and long collection times.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Harnessing drug-related data posted on social media in real-time can offer insights into how the pandemic impacts drug use and monitor misinformation. This study aimed to develop a natural language processing (NLP) pipeline tailored for the analysis of social media discourse on COVID-19\u2013related drugs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study constructed a full pipeline for COVID-19\u2013related drug tweet analysis, using pretrained language model\u2013based NLP techniques as the backbone. This pipeline is architecturally composed of 4 core modules: named entity recognition and normalization to identify medical entities from relevant tweets and standardize them to uniform medication names for time trend analysis, target sentiment analysis to reveal sentiment polarities associated with the entities, topic modeling to understand underlying themes discussed by the population, and drug network analysis to dig potential adverse drug reactions (ADR) and drug-drug interactions (DDI). The pipeline was deployed to analyze tweets related to the COVID-19 pandemic and drug therapies between February 1, 2020, and April 30, 2022.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>From a dataset comprising 169,659,956 COVID-19\u2013related tweets from 103,682,686 users, our named entity recognition model identified 2,124,757 relevant tweets sourced from 1,800,372 unique users, and the top 5 most-discussed drugs: ivermectin, hydroxychloroquine, remdesivir, zinc, and vitamin D. Time trend analysis revealed that the public focused mostly on repurposed drugs (ie, hydroxychloroquine and ivermectin), and least on remdesivir, the only officially approved drug among the 5. Sentiment analysis of the top 5 most-discussed drugs revealed that public perception was predominantly shaped by celebrity endorsements, media hot spots, and governmental directives rather than empirical evidence of drug efficacy. Topic analysis obtained 15 general topics of overall drug-related tweets, with \u201cclinical treatment effects of drugs\u201d and \u201cphysical symptoms\u201d emerging as the most frequently discussed topics. Co-occurrence matrices and complex network analysis further identified emerging patterns of DDI and ADR that could be critical for public health surveillance like better safeguarding public safety in medicines use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study shows that an NLP-based pipeline can be a robust tool for large-scale public health monitoring and can offer valuable supplementary data for traditional epidemiological studies concerning DDI and ADR. The framework presented here aspires to serve as a cornerstone for future social media\u2013based public health analytics.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/63755","type":"journal-article","created":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T08:18:02Z","timestamp":1737793082000},"page":"e63755","source":"Crossref","is-referenced-by-count":10,"title":["Characterizing Public Sentiments and Drug Interactions in the COVID-19 Pandemic Using Social Media: Natural Language Processing and Network Analysis"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-3228","authenticated-orcid":false,"given":"Wanxin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7779-1208","authenticated-orcid":false,"given":"Yining","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-5236","authenticated-orcid":false,"given":"Peilin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3874-4833","authenticated-orcid":false,"given":"Li","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4639-6480","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5696-363X","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2196\/18897"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/19016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/20044"},{"key":"ref4","unstructured":"FDA adverse event reporting system (FAERS)U.S. Food and Drug Administration2025-02-12http:\/\/www.fda.gov\/Drugs\/GuidanceComplianceRegulatoryInformation\/Surveillance\/AdverseDrugEffects\/"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1142\/9789814749411_0045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/clpt.2012.50"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1323"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/2042098619864744"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2125.1988.tb03356.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocu041"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocz009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/2042098618789596"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.12.238"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S326767"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jadohealth.2020.05.030"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583867"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/07448481.2021.1973480"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2196\/44870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2196\/56675"},{"key":"ref21","author":"Jiang, H","year":"2022","journal-title":"arXiv:2201.07281"},{"key":"ref22","unstructured":"ZhouPWangZChongDGuoZHuaYSuZMETS-CoV: a dataset of medical entity and targeted sentiment on COVID-19 related tweets2022NIPS'22: 36th International Conference on Neural Information Processing Systems2022 November 28New Orleans LA USACurran Associates Inc2191621932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107126"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3001216"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2196\/22624"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app112110442"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2196\/24585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2196\/31540"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2196\/19273"},{"key":"ref30","unstructured":"DevlinJChangMWLeeKToutanovaKBert: Pre-training of deep bidirectional transformers for language understanding2018Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)2025 February 09Minneapolis, MinnesotaAssociation for Computational Linguistics181004805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2015.2489653"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2017.2788182"},{"key":"ref34","unstructured":"WangJYuL-CZhangXSoftMCL: soft momentum contrastive learning for fine-grained sentiment-aware pre-training2024Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)2025 February 09Torino, ItaliaELRA and ICCL1501215023"},{"key":"ref35","unstructured":"RehurekRSojkaPSoftware framework for topic modelling with large corpora2010Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks2010 July 25Malta"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab098"},{"key":"ref37","unstructured":"StevensKKegelmeyerPAndrzejewskiDButtlerDExploring topic coherence over many models and many topics2012Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning2012 July 12-14Jeju Island Korea952961"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2196\/45419"},{"key":"ref39","unstructured":"AboutGephi2025-02-12https:\/\/gephi.org\/about\/"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0098679"},{"key":"ref41","unstructured":"ATC\/DDD index 2025Norwegian Institute of Public Health2025-02-12https:\/\/www.whocc.no\/atc_ddd_index\/"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae118"},{"key":"ref43","unstructured":"RahutomoFKitasukaTAritsugiMSemantic cosine similarity2012The 7th International Student Conference on Advanced Science and Technology ICAST 20122012 October 29-30Seoul, South Korea"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.02.024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD014962"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.34172\/jnp.2021.10"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.29024\/ijsm.64"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/s0735-1097(21)03393-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/p10008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1186\/s41231-021-00091-4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2020.589379"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2165\/00003495-200363080-00004"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.1157"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2196\/17917"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103500"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-018-1247-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1097\/PCC.0000000000002474"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2022.01.015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac114"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.2196\/39676"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.2196\/24435"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2196\/26780"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1056\/aira2400012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dkad295"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1002\/jmv.29018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s40265-023-01926-0"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1111\/ene.16017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2196\/39484"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-019-00858-7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1002\/hast.1525"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare9020151"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.2196\/16661"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1136\/bmjgh-2023-013515"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1504\/ijwgs.2020.106103"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm6807a2"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.2196\/42227"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.2196\/21978"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2196\/34306"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ichi.2013.10"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67964-8_23"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-015-0333-5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/srep17357"},{"key":"ref83","unstructured":"BrownTMannBRyderNSubbiahMKaplanJDhariwalPNeelakantanAShyamPSastryGAskellAAgarwalSHerbert-VossAKruegerGHenighanTChild,RRameshAZieglerDMWuJWinterCHesseCChenMSiglerELitwinMGray,SChessBClarkJBernerCMcCandlishSRadfordASutskeverIAmodeiDLanguage models are few-shot learners2020NIPS'20: 34th International Conference on Neural Information Processing Systems2020 December 6 - 12Vancouver BC Canada18771901"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae079"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-3283-6"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0246265"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.690726"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciac014"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0262564"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-019-00807-4"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-022-01170-7"},{"key":"ref93","unstructured":"WojcikSHughesASizing up twitter usersPew Research Center20192025-02-12https:\/\/www.pewresearch.org\/internet\/2019\/04\/24\/sizing-up-twitter-users\/"},{"key":"ref94","unstructured":"WojcikSHughesASizing up twitter usersPEW Research Center20192025-02-12https:\/\/www.pewresearch.org\/internet\/2019\/04\/24\/sizing-up-twitter-users\/"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e63755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:56:33Z","timestamp":1785851793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e63755"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,5]]},"references-count":94,"URL":"https:\/\/doi.org\/10.2196\/63755","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.63755","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,5]]}}}