{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:26:15Z","timestamp":1790699175178,"version":"4.1.0"},"reference-count":101,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"\n Background<\/jats:title>\n Depression affects more than 350 million people globally. Traditional diagnostic methods have limitations. Analyzing textual data from social media provides new insights into predicting depression using machine learning. However, there is a lack of comprehensive reviews in this area, which necessitates further research.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This review aims to assess the effectiveness of user-generated social media texts in predicting depression and evaluate the influence of demographic, language, social media activity, and temporal features on predicting depression on social media texts through machine learning.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We searched studies from 11 databases (CINHAL [through EBSCOhost], PubMed, Scopus, Ovid MEDLINE, Embase, PubPsych, Cochrane Library, Web of Science, ProQuest, IEEE Explore, and ACM digital library) from January 2008 to August 2023. We included studies that used social media texts, machine learning, and reported area under the curve, Pearson r, and specificity and sensitivity (or data used for their calculation) to predict depression. Protocol papers and studies not written in English were excluded. We extracted study characteristics, population characteristics, outcome measures, and prediction factors from each study. A random effects\u00a0model was used to extract the effect sizes with 95% CIs. Study heterogeneity was evaluated using forest plots and P values in the Cochran Q test. Moderator analysis was performed to identify the sources of heterogeneity.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n A total of 36 studies were included. We observed a significant overall correlation between social media texts and depression, with a large effect size (r=0.630, 95% CI 0.565-0.686). We noted the same correlation and large effect size for demographic (largest effect size; r=0.642, 95% CI 0.489-0.757), social media activity (r=0.552, 95% CI 0.418-0.663), language (r=0.545, 95% CI 0.441-0.649), and temporal features (r=0.531, 95% CI 0.320-0.693). The social media platform type (public or private; P<.001), machine learning approach (shallow or deep; P=.048), and use of outcome measures (yes or no; P<.001) were significant moderators. Sensitivity analysis revealed no change in the results, indicating result stability. The Begg-Mazumdar rank correlation (Kendall \u03c4b=0.22063; P=.058) and the Egger test (2-tailed t34=1.28696; P=.207) confirmed the absence of publication bias.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Social media textual content can be a useful tool for predicting depression. Demographics, language, social media activity, and temporal features should be considered to maximize the accuracy of depression prediction models. Additionally, the effects of social media platform type, machine learning approach, and use of outcome measures in depression prediction models need attention. Analyzing social media texts for depression prediction is challenging, and findings may not apply to a broader population. Nevertheless, our findings offer valuable insights for future research.<\/jats:p>\n <\/jats:sec>\n \n Trial Registration<\/jats:title>\n PROSPERO CRD42023427707; https:\/\/www.crd.york.ac.uk\/PROSPERO\/view\/CRD42023427707<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/59002","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T16:00:27Z","timestamp":1744387227000},"page":"e59002","source":"Crossref","is-referenced-by-count":26,"title":["Text-Based Depression Prediction on Social Media Using Machine Learning: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6098-6564","authenticated-orcid":false,"given":"Doreen","family":"Phiri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2689-173X","authenticated-orcid":false,"given":"Frank","family":"Makowa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1312-6131","authenticated-orcid":false,"given":"Vivi Leona","family":"Amelia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2376-4188","authenticated-orcid":false,"given":"Yohane Vincent Abero","family":"Phiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7460-4817","authenticated-orcid":false,"given":"Lindelwa Portia","family":"Dlamini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0517-5913","authenticated-orcid":false,"given":"Min-Huey","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,11]]},"reference":[{"key":"ref1","unstructured":"MarcusMYasamyMTvan OmmerenMVChisholmDSaxenaSDepression: A global public health concernWorld Health Organization20122024-07-16https:\/\/www.researchgate.net\/publication\/285075782_Depression_A_global_public_health_concern"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.12.107"},{"key":"ref3","year":"2013","journal-title":"Diagnostic and Statistical Manual of Mental Disorders (DSM-5-TR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2196\/27244"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/536"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10020291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0233-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.paid.2017.12.018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.01.043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5121\/ijscai.2016.5105"},{"key":"ref12","author":"Zhang, Z","year":"2022","journal-title":"ArXiv. Preprint posted online on May 23, 2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2017.07.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/17445760.2022.2070748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10299-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1089\/cyber.2017.0384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/bibm55620.2022.9994921"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0165551519860469"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1037\/pspp0000187"},{"key":"ref20","first-page":"39","volume":"4","author":"T\u00f8lb\u00f8ll, KB","year":"2019","journal-title":"J Lang Works"},{"key":"ref21","first-page":"124","volume":"98","author":"Zulkarnain, N","year":"2020","journal-title":"J Theor Appl Inf Technol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v2i1.18623"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/mental.5842"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702280"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654945"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675139"},{"key":"ref27","unstructured":"Vr'nakDPaulinovicMKuzinaVEarly Depression Detection Using Temporal and Sentiment Features20192023-10-22Zagreb, CroatiaUniversity of Zagrebhttps:\/\/www.fer.unizg.hr\/_download\/repository\/TAR-2019-ProjectReports.pdf#page=72"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191624"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-981-19-1724-0_6","author":"Biswas, S","year":"2022","journal-title":"Predictive Analytics of Psychological Disorders in Healthcare"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2022.08.070"},{"key":"ref31","unstructured":"GuptaGKSharmaDKDepression detection on social media with the aid of machine learning platform: a comprehensive survey20218th International Conference on Computing for Sustainable Global Development (INDIACom)March 17-19, 2021New Delhi, India"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2021.0522"},{"key":"ref33","unstructured":"EndNoteClarivate20132023-12-05https:\/\/support.clarivate.com\/Endnote\/s\/article\/Citing-the-EndNote-program-as-a-reference?language=en_US"},{"key":"ref34","first-page":"231","author":"Rosenthal, R","year":"1994","journal-title":"The Handbook of Research Synthesis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.13.1.19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/s0895-4356(03)00177-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00863"},{"key":"ref38","first-page":"121","author":"Borenstein, M","year":"2020","journal-title":"Introduction to Meta-Analysis"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.12"},{"key":"ref40","author":"Cohen, J","year":"1988","journal-title":"Statistical Power Analysis for the Behavioral Sciences"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1186"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejvs.2010.07.011"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.pubrev.2020.101980"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1002\/0470870168.ch5","author":"Sterne, JAC","year":"2005","journal-title":"Publication Bias in Meta\u2010Analysis: Prevention, Assessment and Adjustments"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1002\/0470870168.ch6","author":"Sterne, JAC","year":"2005","journal-title":"Regression Methods to Detect Publication and Other Bias in Meta-Analysis"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1002\/0470870168.ch8","author":"Duval, S","year":"2005","journal-title":"Publication Bias in Meta-Analysis: Prevention, Assessment and Adjustments"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISADS.2017.41"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SPICSCON48833.2019.9065101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7276"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v7i1.14432"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.13052\/jwe1540-9589.19344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICTACS56270.2022.9988489"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICESC51422.2021.9532838"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583867"},{"key":"ref56","unstructured":"R\u00edssolaEABahrainianSACrestaniFAnticipating depression based on online social media behaviour201913th International Conference on Flexible Query Answering SystemsJuly 2-5, 2019Amantea, Italy"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3340631.3394879"},{"key":"ref58","author":"Yohapriyaa, M","year":"2022","journal-title":"Intelligent Data Communication Technologies and Internet of Things: Intelligent Data Communication Technologies and Internet of Things: Proceedings of ICICI 2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-018-0533-4"},{"key":"ref60","unstructured":"WongkoblapAVadilloMACurcinVA multilevel predictive model for detecting social network users with depression20182018 IEEE International Conference on Healthcare Informatics (ICHI)June 4-7, 2018New York, NY"},{"key":"ref61","author":"Wang, X","year":"2013","journal-title":"Trends and Applications in Knowledge Discovery and Data Mining"},{"key":"ref62","doi-asserted-by":"crossref","unstructured":"VictorDBKawsherJLabibMSLatifSMachine learning techniques for depression analysis on social media\u2014case study on Bengali community20202020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)November 5-7, 2020Coimbatore, India","DOI":"10.1109\/ICECA49313.2020.9297436"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3145634"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.2983035"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3569580"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCSS57650.2023.10169826"},{"key":"ref67","unstructured":"StankevichMLatyshevAKuminskayaESmirnovIGrigorievODepression detection from social media texts2019CEUR Workshop ProceedingsOctober 15-18, 2019Kazan, Russia"},{"key":"ref68","author":"Shekerbekova, S","year":"2021","journal-title":"Advanced Informatics for Computing Research"},{"key":"ref69","author":"Saini, G","year":"2022","journal-title":"Security, Privacy and Data Analytics: Select Proceedings of ISPDA 2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2196\/11817"},{"key":"ref71","doi-asserted-by":"crossref","unstructured":"NarynovSMukhtarkhanulyDOmarovBKozhakhmetKOmarovBMachine learning approach to identifying depression related posts on social media20202020 20th International Conference on Control, Automation and Systems (ICCAS)Busan, South KoreaOctober 13-16, 2020","DOI":"10.23919\/ICCAS50221.2020.9268336"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v14i1.7313"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICPS55917.2022.00023"},{"key":"ref74","first-page":"633","author":"Kumar, A","year":"2021","journal-title":"Machine Vision and Augmented Intelligence\u2014Theory and Applications: Select Proceedings of MAI 2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV57592.2022.10004238"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7224"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2022.107503"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IC4ME2.2018.8465641"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/IS57118.2022.10019625"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-12961-9"},{"key":"ref81","first-page":"42","author":"Mari\u00f1elarena-Dondena, L","year":"2017","journal-title":"Panam J Neuropsychol"},{"key":"ref82","doi-asserted-by":"crossref","first-page":"118","DOI":"10.3115\/v1\/W14-3214","author":"Schwartz, HA","year":"2014","journal-title":"Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality"},{"key":"ref83","unstructured":"MahnkenKSurvey: More young people are depressed during the pandemicThe 7420172023-10-21https:\/\/www.the74million.org\/survey-more-young-people-are-depressed-during-the-pandemic-but-they-may-be-using-social-media-to-cope\/"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpbup.2022.100066"},{"key":"ref85","unstructured":"AmedieJThe Impact of Social Media on Society [dissertation]20152025-02-25Santa Clara, CASanta Clara Universityhttp:\/\/scholarcommons.scu.edu\/engl_176\/2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-3214"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v13i01.3225"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0275004"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1802331115"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.01045"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3415215"},{"key":"ref92","unstructured":"BenamaraFMoriceauVMotheJRamiandrisoaFHeZAutomatic detection of depressive users in social media2018Conf\u00e9rence francophone en Recherche d'Information et Applications (CORIA)April 3-4, 2024La Rochelle, France"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.2196\/mental.8141"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2012.11.012"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-18305-3_1","author":"El Naqa, I","year":"2015","journal-title":"Machine Learning in Radiation Oncology: Theory and Applications"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.dibe.2021.100045"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.3390\/app12031645"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.04674"},{"key":"ref99","author":"Salehinejad, H","year":"2017","journal-title":"ArXiv. Preprint posted online on December 27, 2017"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-019-0681-4"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0327(03)00198-8"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e59002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:52:44Z","timestamp":1785851564000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e59002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,11]]},"references-count":101,"URL":"https:\/\/doi.org\/10.2196\/59002","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.59002","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,11]]}}}