{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T06:44:38Z","timestamp":1792219478651,"version":"4.4.0"},"reference-count":83,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Infodemiology"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The COVID-19 pandemic intensified the challenges associated with mental health and substance use (SU), with societal and economic upheavals leading to heightened stress and increased reliance on drugs as a coping mechanism. Centers for Disease Control and Prevention data from June 2020 showed that 13% of Americans used substances more frequently due to pandemic-related stress, accompanied by an 18% rise in drug overdoses early in the year. Simultaneously, a significant increase in social media engagement provided unique insights into these trends. Our study analyzed social media data from January 2019 to December 2021 to identify changes in SU patterns across the pandemic timeline, aiming to inform effective public health interventions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to analyze SU from large-scale social media data during the COVID-19 pandemic, including the prepandemic and postpandemic periods as baseline and consequence periods. The objective was to examine the patterns related to a broader spectrum of drug types with underlying themes, aiming to provide a more comprehensive understanding of SU trends during the COVID-19 pandemic.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We leveraged a deep learning model, Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa), to analyze 1.13 billion Twitter (subsequently rebranded X) posts from January 2019 to December 2021, aiming to identify SU posts. The model\u2019s performance was enhanced by a human-in-the-loop strategy that subsequently enriched the annotated data used during the fine-tuning phase. To gain insights into SU trends over the study period, we applied a range of statistical techniques, including trend analysis, k-means clustering, topic modeling, and thematic analysis. In addition, we integrated the system into a real-time application designed for monitoring and preventing SU within specific geographic locations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our research identified 9 million SU posts in the studied period. Compared to 2019 and 2021, the most substantial display of SU-related posts occurred in 2020, with a sharp 21% increase within 3 days of the global COVID-19 pandemic declaration. Alcohol and cannabinoids remained the most discussed substances throughout the research period. The pandemic particularly influenced the rise in nonillicit substances, such as alcohol, prescription medication, and cannabinoids. In addition, thematic analysis highlighted COVID-19, mental health, and economic stress as the leading issues that contributed to the influx of substance-related posts during the study period.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates the potential of leveraging social media data for real-time detection of SU trends during global crises. By uncovering how factors such as mental health and economic stress drive SU spikes, particularly in alcohol and prescription medication, we offer crucial insights for public health strategies. Our approach paves the way for proactive, data-driven interventions that will help mitigate the impact of future crises on vulnerable populations.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/59076","type":"journal-article","created":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T13:45:06Z","timestamp":1740923106000},"page":"e59076","source":"Crossref","is-referenced-by-count":9,"title":["Large-Scale Deep Learning\u2013Enabled Infodemiological Analysis of Substance Use Patterns on Social Media: Insights From the COVID-19 Pandemic"],"prefix":"10.2196","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3390-0259","authenticated-orcid":false,"given":"Julina","family":"Maharjan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-3696","authenticated-orcid":false,"given":"Jianfeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3794-5828","authenticated-orcid":false,"given":"Jennifer","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1032-8275","authenticated-orcid":false,"given":"NhatHai","family":"Phan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2852-5776","authenticated-orcid":false,"given":"Deric","family":"Kenne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1895-4243","authenticated-orcid":false,"given":"Ruoming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"ref1","unstructured":"Drug abuse statisticsNational Center of Drug Abuse Statistics2023-10-20https:\/\/drugabusestatistics.org\/"},{"key":"ref2","unstructured":"Drug overdose deaths in the United States, 2003-2023Centers for Disease Control and Prevention20242025-03-31https:\/\/www.cdc.gov\/nchs\/products\/databriefs\/db522.htm"},{"key":"ref3","unstructured":"Addiction and substance misuse reports and publicationsUS Department of Health and Human Services2023-08-10https:\/\/www.hhs.gov\/surgeongeneral\/reports-and-publications\/addiction-and-substance-misuse\/index.html"},{"key":"ref4","unstructured":"Covid-19 and substance useNational Institute on Drug Abuse2023-08-14https:\/\/nida.nih.gov\/research-topics\/covid-19-substance-use"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2020.113096"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7326\/m20-1212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2009609117"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18775\/ijied.1849-7551-7020.2015.61.2005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2020.1562"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00127-020-01924-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm6932a1"},{"key":"ref12","unstructured":"AlterAYeagerCCOVID-19 impact on US national overdose crisisOverdose Detection Mapping Application Program2023-08-14https:\/\/www.odmap.org\/content\/docs\/news\/2020\/odmap-report-june-2020.pdf"},{"key":"ref13","unstructured":"COVID-19 and the drug supply chain: from production and trafficking to useUnited Nations Office on Drugs and Crime20202025-03-27https:\/\/www.unodc.org\/documents\/data-and-analysis\/covid\/Covid-19-and-drug-supply-chain-Mai2020.pdf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph19042230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2021.646206"},{"key":"ref16","unstructured":"BeechMCOVID-19 pushes up internet use 70% and streaming more than 12%, first figures revealForbes202003252023-09-27https:\/\/www.forbes.com\/sites\/markbeech\/2020\/03\/25\/covid-19-pushes-up-internet-use-70-streaming-more-than-12-first-figures-reveal\/?sh=337c58783104"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18126318"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2196\/19556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231924"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10389-022-01751-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2023.107795"},{"key":"ref22","author":"Graig, L","year":"2021","journal-title":"Mental Health and Substance Use Disorders in the Era of COVID-19: The Impact of the Pandemic on Communities of Color: Proceedings of a Workshop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10964-019-01024-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2020.108017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/ntr\/ntaa003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0200105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10964-012-9869-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsx.2020.06.008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/02791072.2021.1992048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15190\/d.2021.20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2020.113407"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2021.653674"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/jcph.1937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2020.00700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ypmed.2021.106422"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2020.571084"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2021.109150"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17134677"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1186\/s13011-022-00442-w"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI200479"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1211\/PJ.2020.20208538"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1089\/pop.2020.0230"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.7326\/m20-1141"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/ijcp.14012"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.addbeh.2021.106917"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.34172\/ahj.2022.1274"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10389-020-01443-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.54566"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph19042230"},{"key":"ref50","unstructured":"Key substance and mental health indicators in the United States: results from the 2020 National Survey on Drug Use and HealthSubstance Abuse and Mental Health Services Administration2023-08-14https:\/\/www.samhsa.gov\/data\/sites\/default\/files\/reports\/rpt35325\/NSDUHFFRPDFWHTMLFiles2020\/2020NSDUHFFR1PDFW102121.pdf"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300354"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.2503"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.5144"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0071-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-015-0379-4"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icde.2017.221"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7276"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.14672"},{"key":"ref59","author":"Vaswani, A","year":"2025","journal-title":"arXiv. Preprint posted online on June 12, 2017"},{"key":"ref60","author":"Liu, Y","year":"2025","journal-title":"arXiv. Preprint posted online on July 26, 2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01560-1","author":"Settles, B","year":"2012","journal-title":"Active Learning"},{"key":"ref63","unstructured":"The Twitter stream grabInternet Archive20212022-09-30https:\/\/archive.org\/details\/twitterstream"},{"key":"ref64","author":"Devlin, J","year":"2025","journal-title":"arXiv. Preprint posted online on October 11, 2018"},{"key":"ref65","unstructured":"Commonly abused drugsNational Institute on Drug Abuse2022-09-24https:\/\/nida.nih.gov\/sites\/default\/files\/cadchart.pdf"},{"key":"ref66","unstructured":"Slang terms and code words: a reference for law enforcement personnelDrug Enforcement Administration Intelligence Report20182025-03-27https:\/\/ndews.umd.edu\/sites\/ndews.umd.edu\/files\/dea-drug-slang-terms-and-code-words-july2018.pdf"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.addbeh.2021.107213"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1186\/s13722-022-00303-8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.22365\/jpsych.2022.072"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropharm.2021.108766"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0082"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.16409.98405"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.2307\/2281868"},{"key":"ref74","unstructured":"Welcome to the FactorAnalyzer documentation!FactorAnalyzer2023-03-03https:\/\/factor-analyzer.readthedocs.io\/en\/latest\/[accessed"},{"key":"ref75","author":"Gorsuch, RL","year":"1983","journal-title":"Factor Analysis Second Edition"},{"key":"ref76","unstructured":"Elastic Stack homepageElastic Stack2023-01-01https:\/\/www.elastic.co\/elastic-stack"},{"key":"ref77","unstructured":"Logstash 7.17.0 Release NotesElastic2022-12-27https:\/\/www.elastic.co\/guide\/en\/logstash\/7.17\/logstash-7-17-0.html"},{"key":"ref78","unstructured":"MongoDB homepageMongoDB2022-12-01https:\/\/www.mongodb.com\/"},{"key":"ref79","unstructured":"OpenAI homepageOpenAI2023-12-01https:\/\/openai.com\/api\/"},{"key":"ref80","unstructured":"Northeast Ohio tri-county prevention infrastructureKent State University2025-03-27https:\/\/www.kent.edu\/mhsu\/tcpi"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref82","author":"Moradi, M","year":"2025","journal-title":"arXiv. Preprint posted online on September 6, 2021"},{"key":"ref83","unstructured":"JulinaM \/ robertaForTweetAnalysisGithub2025-03-27https:\/\/github.com\/JulinaM\/robertaForTweetAnalysis"}],"container-title":["JMIR Infodemiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/infodemiology.jmir.org\/2025\/1\/e59076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:52:50Z","timestamp":1785851570000},"score":1,"resource":{"primary":{"URL":"https:\/\/infodemiology.jmir.org\/2025\/1\/e59076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,17]]},"references-count":83,"URL":"https:\/\/doi.org\/10.2196\/59076","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.59076","asserted-by":"object"}]},"ISSN":["2564-1891"],"issn-type":[{"value":"2564-1891","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,17]]}}}