{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:53:22Z","timestamp":1775220802926,"version":"3.50.1"},"reference-count":69,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information Systems Research"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>Short-form video platforms such as TikTok and Douyin are widely used but have sparked serious concerns about their impact on youth mental health, especially suicidal thoughts. This study introduces a novel knowledge-guided neural topic model that predicts a video\u2019s potential to induce suicidal thoughts in viewers at the time of upload. Unlike existing models, our approach integrates medical knowledge on suicide risk factors with user-generated content to improve prediction accuracy and explainability. Tested on real-world data from two major platforms, the model not only outperforms current machine learning and deep learning benchmarks but also uncovers emerging content themes linked to suicidal thought risk. For practice, this tool can be directly integrated into platforms\u2019 content moderation pipelines, identifying high-risk videos for follow-up human review before harm spreads. For policy, it offers a scalable and ethically informed method to mitigate digital risks to youth mental health, balancing user safety with content creator rights. This work offers a critical step forward in responsible AI and public mental health protection in the era of algorithm-driven media.<\/jats:p>","DOI":"10.1287\/isre.2024.1071","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T11:53:57Z","timestamp":1750679637000},"page":"356-377","source":"Crossref","is-referenced-by-count":1,"title":["Short-Form Videos and Mental Health: A Knowledge-Guided Neural Topic Model"],"prefix":"10.1287","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9415-3726","authenticated-orcid":false,"given":"Jiaheng","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Accounting & MIS, Lerner College of Business and Economics, University of Delaware, Newark, Delaware 19716"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0260-7589","authenticated-orcid":false,"given":"Yidong","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Management, Hefei University of Technology, Hefei 230009, China; and Department of Information Systems, City University of Hong Kong, Hong Kong 999077, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-2657","authenticated-orcid":false,"given":"Ruicheng","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Management Science and Engineering, Anhui University of Finance and Economics, Bengbu 233030, China; and School of Management, Hefei University of Technology, Hefei 230009, China; and Key Laboratory of Philosophy and Social Sciences for Cyberspace Behaviour and Management, Hefei 230009, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Management, Hefei University of Technology, Hefei 230009, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel Dajun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2024.editorial.v35.n2"},{"key":"B2","doi-asserted-by":"crossref","unstructured":"An M, Wang J, Li S, Zhou G (2020) Multimodal topic-enriched auxiliary learning for depression detection.\n                      Proc. 28th Internat. Conf. Comput. Linguistics (Barcelona, Spain (Online))\n                      (International Committee on Computational Linguistics), 1078\u20131089.","DOI":"10.18653\/v1\/2020.coling-main.94"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.05.074"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20032383"},{"key":"B71","unstructured":"Blei DM, McAuliffe JD (2007) Supervised topic models.\n                      Proc. 21st Internat. Conf. Neural Inform. Processing Systems (NIPS\u201907)\n                      (Curran Associates Inc., Red Hook, NY), 121\u2013128."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"B6","first-page":"993","volume":"3","author":"Blei DM","year":"2003","journal-title":"J. Machine Learn. Res."},{"key":"B7","unstructured":"Bloomberg (2023) TikTok\u2019s algorithm keeps pushing suicide to vulnerable kids. (April 20), https:\/\/www.bloomberg.com\/news\/features\/2023-04-20\/tiktok-effects-on-mental-health-in-focus-after-teen-suicide."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1001\/jamapediatrics.2019.1759"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1257\/aer.20211218"},{"key":"B10","unstructured":"ByteDance (2024) Community guidelines. Accessed May 4, 2025, https:\/\/www.tiktok.com\/community-guidelines\/en."},{"key":"B11","author":"Cao Z","year":"2015","journal-title":"Proc. Twenty-Ninth AAAI Conf. Artificial Intelligence"},{"key":"B12","doi-asserted-by":"crossref","unstructured":"Card D, Tan C, Smith NA (2018) Neural models for documents with metadata.\n                      Proc. 56th Annual Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)\n                      (Association for Computational Linguistics, Stroudsburg, PA), 2031\u20132040.","DOI":"10.18653\/v1\/P18-1189"},{"key":"B13","unstructured":"Carpenter A (2023) Associations between TikTok use, mental health, and body image among college students. Honors theses, University of Mississippi, University."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121588"},{"key":"B15","doi-asserted-by":"crossref","unstructured":"Chang Y-S, Hung W-C, Juang T-Y (2013) Depression diagnosis based on ontologies and Bayesian networks.\n                      2013 IEEE Internat. Conf. Systems Man Cybernetics (Manchester, UK)\n                      , 3452\u20133457.","DOI":"10.1109\/SMC.2013.589"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-022-00704-w"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/app13074595"},{"key":"B18","unstructured":"DBSA (2024) The alliance insider: TikTok and youth mental health 2024. Accessed May 4, 2025, https:\/\/www.dbsalliance.org\/education\/newsletters\/tiktok-and-youth-mental-health\/."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00325"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3084154"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.015"},{"key":"B22","unstructured":"Jagarlamudi J, Daum\u00e9 H III, Udupa R (2012) Incorporating lexical priors into topic models.\n                      Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguistics (EACL \u201912)\n                      (Association for Computational Linguistics, Stroudsburg, PA), 204\u2013213."},{"key":"B70","unstructured":"Jargon J (2023) TikTok feeds teens a diet of darkness.\n                      Wall Street Journal\n                      (May 13), https:\/\/www.wsj.com\/tech\/personal-tech\/tiktok-feeds-teens-a-diet-of-darkness-8f350507?gaa_at=eafs&gaa_n=ASWzDAhEULzVQOjDqoxTtT-YczUWAFhCXH1YWsEsDrAbMa4oNcoTU0TaArkk2nVC-Ik%3D&gaa_ts=683f7853&gaa_sig=P6qHYvshKvAgGGafW5WPHKgLIUogPotQtaB-8842u20P5IEwWKypuUajeqc88u-z5F2EJ8ohrqMOjbzWt1ZUA%3D%3D."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7452"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2022\/17141"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.07.004"},{"key":"B27","doi-asserted-by":"crossref","unstructured":"Lin Y, Gao X, Chu X, Wang Y, Zhao J, Chen C (2023) Enhancing neural topic model with multi-level supervisions from seed words.\n                      Findings Assoc. Comput. Linguistics: ACL 2023\n                      (Association for Computational Linguistics, Toronto), 13361\u201313377.","DOI":"10.18653\/v1\/2023.findings-acl.845"},{"key":"B28","unstructured":"LiveWorld (2023) Social channels gain credibility with healthcare practitioners. Accessed May 4, 2025, https:\/\/info.liveworld.com\/hubfs\/HCP-Social-Media-Pharma-Marketing-Survey-eBook-LiveWorld.pdf."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18031041"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1177\/13591045221106608"},{"key":"B32","doi-asserted-by":"crossref","unstructured":"Milton A, Ajmani L, DeVito MA, Chancellor S (2023) \u201cI see me here\u201d: Mental health content, community, and algorithmic curation on TikTok.\n                      Proc. 2023 CHI Conf. Human Factors Comput. Systems (CHI \u201923)\n                      (Association for Computing Machinery, New York), Article 480, 1\u201317.","DOI":"10.1145\/3544548.3581489"},{"key":"B33","doi-asserted-by":"crossref","unstructured":"Momeni E, Sageder G (2013) An empirical analysis of characteristics of useful comments in social media.\n                      Proc. 5th Annual ACM Web Sci. Conf. (WebSci \u201913)\n                      (Association for Computing Machinery, New York), 258\u2013261.","DOI":"10.1145\/2464464.2464490"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v7i1.14410"},{"key":"B35","unstructured":"NY Times (2024) Surgeon general calls for warning labels on social media platforms. (June 17), https:\/\/www.nytimes.com\/2024\/06\/17\/health\/surgeon-general-social-media-warning-label.html."},{"key":"B36","unstructured":"Oberlo (2024) Tiktok users by country (2024). Accessed May 4, 2025, https:\/\/www.oberlo.com\/statistics\/tiktok-users-by-country."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2022\/461E1"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3223999"},{"key":"B39","unstructured":"Paul K (2022) What TikTok does to your mental health: \u2018It\u2019s embarrassing we know so little\u2019.\n                      The Guardian\n                      (October 30), https:\/\/www.theguardian.com\/technology\/2022\/oct\/30\/tiktok-mental-health-social-media."},{"key":"B40","doi-asserted-by":"crossref","unstructured":"Qu M (2022) The study on Tik Tok interactive modes and future interactive video strategy development.\n                      2022 8th Internat. Conf. Humanities Social Sci. Res. (ICHSSR 2022)\n                      (Atlantis Press, Dordrecht, Netherlands), 1746\u20131750.","DOI":"10.2991\/assehr.k.220504.316"},{"key":"B41","doi-asserted-by":"crossref","unstructured":"Ray A, Kumar S, Reddy R, Mukherjee P, Garg R (2019) Multi-level attention network using text, audio and video for depression prediction.\n                      Proc. 9th Internat. Audio\/Visual Emotion Challenge Workshop (AVEC \u201919)\n                      (Association for Computing Machinery, New York), 81\u201388.","DOI":"10.1145\/3347320.3357697"},{"key":"B42","unstructured":"Reed J (2021) Using NLP-based text mining to gather patient insights from social media at Roche. Accessed May 4, 2025, https:\/\/www.linguamatics.com\/blog\/using-nlp-based-text-mining-gather-patient-insights-social-media-roche."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1141684"},{"key":"B44","unstructured":"Schlott R (2022) How TikTok has become a dangerous breeding ground for mental disorders.\n                      New York Post\n                      (March 12), https:\/\/nypost.com\/2022\/03\/12\/tiktok-has-become-a-dangerous-mental-disorder-breeding-ground\/."},{"key":"B45","volume-title":"Blackwell Guide to the Philosophy of Computing and Information","author":"Smith B","year":"2003"},{"key":"B46","unstructured":"Social Shepherd (2025) 25 essential TikTok statistics you need to know in 2025. Accessed May 4, 2025, https:\/\/thesocialshepherd.com\/blog\/tiktok-statistics."},{"key":"B47","author":"Srivastava A","year":"2016","journal-title":"Proc. Internat. Conf. Learn. Representations"},{"key":"B48","unstructured":"Statista (2023) TikTok effects on mental health and digital addiction concerns among users in the United States as of May 2023. Accessed May 4, 2025, https:\/\/www.statista.com\/statistics\/1409776\/tiktom-us-opinions-mental-health-effects\/#:\u223c:text=According%20to%20a%20survey%20conducted,result%20of%20using%20the%20app."},{"key":"B49","unstructured":"Statista (2024) Breakdown of Weibo users in China as of September 2022, by age group. Accessed May 4, 2025, https:\/\/www.statista.com\/statistics\/320940\/china-sina-weibo-user-breakdown-by-age-group\/."},{"key":"B50","unstructured":"Stevens K, Kegelmeyer P, Andrzejewski D, Buttler D (2012) Exploring topic coherence over many models and many topics.\n                      Proc. 2012 Joint Conf. Empirical Methods Natural Language Processing Comput. Natural Language Learn.\n                      (Association for Computational Linguistics, Stroudsburg, PA), 952\u2013961."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909180"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1108\/ITP-04-2020-0186"},{"key":"B53","doi-asserted-by":"crossref","unstructured":"Toto E, Tlachac ML, Rundensteiner EA (2021) AudiBERT: A deep transfer learning multimodal classification framework for depression screening.\n                      Proc. 30th ACM Internat. Conf. Inform. Knowledge Management (CIKM \u201921)\n                      (Association for Computing Machinery, New York), 4145\u20134154.","DOI":"10.1145\/3459637.3481895"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2885515"},{"key":"B56","unstructured":"Wang X, Yang Y (2020) Neural topic model with attention for supervised learning.\n                      Proc. Internat. Conf. Artificial Intelligence Statist\n                      . (PMLR, New York), 1147\u20131156."},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.109"},{"key":"B58","unstructured":"Yaguara (2025) Short form video statistics of 2025 (usage & trends). Accessed May 4, 2025, https:\/\/www.yaguara.co\/short-form-video-statistics\/#:~:text=in%20current%20times.Short%20Form%20Video%20Statistics%3A%20Top%20Picks%20(2025),to%20use%20short%2Dform%20videos."},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2022.1124"},{"key":"B60","doi-asserted-by":"crossref","unstructured":"Yang L, Jiang D, He L, Pei E, Oveneke MC, Sahli H (2016) Decision tree based depression classification from audio video and language information.\n                      Proc. 6th Internat. Workshop Audio\/Visual Emotion Challenge (AVEC \u201916)\n                      (Association for Computing Machinery, New York), 89\u201396.","DOI":"10.1145\/2988257.2988269"},{"key":"B61","doi-asserted-by":"crossref","unstructured":"Yang L, Sahli H, Xia X, Pei E, Oveneke MC, Jiang D (2017) Hybrid depression classification and estimation from audio video and text information.\n                      Proc. 7th Ann. Workshop Audio\/Visual Emotion Challenge (AVEC \u201917)\n                      (Association for Computing Machinery, New York), 45\u201351.","DOI":"10.1145\/3133944.3133950"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21483"},{"key":"B63","doi-asserted-by":"crossref","unstructured":"Yu Y, Zhuang Y, Zhang J, Meng Y, Ratner A, Krishna R, Shen J, Zhang C (2023) Large language model as attributed training data generator: A tale of diversity and bias.\n                      Proc. 37th Internat. Conf. Neural Inform. Processing Systems (NIPS \u201923)\n                      (Curran Associates Inc., Red Hook, NY), Article 2433, 55734\u201355784.","DOI":"10.52202\/075280-2433"},{"issue":"10","key":"B64","first-page":"1490","volume":"6","author":"Zahra MF","year":"2022","journal-title":"J. Positive School Psych."},{"key":"B65","unstructured":"Zhai K, Boyd-Graber J (2013) Online latent Dirichlet allocation with infinite vocabulary.\n                      Proc. 30th Internat. Conf. Internat. Conf. Machine Learn. (ICML\u201913)\n                      , vol. 28 (JMLR.org), I-561\u2013I-569."},{"key":"B66","author":"Zhang H","year":"2018","journal-title":"Proc. Internat. Conf. Learn. Representations"},{"key":"B67","author":"Zhang D","year":"2024","journal-title":"Inform. Systems Res."},{"key":"B68","doi-asserted-by":"crossref","unstructured":"Zhao H, Phung D, Huynh V, Jin Y, Du L, Buntine W (2021) Topic modelling meets deep neural networks: A survey\n                      . P\n                      roc. Internat. Joint Conf. Artificial Intelligence\n                      (OpenReview.net).","DOI":"10.24963\/ijcai.2021\/638"},{"key":"B69","unstructured":"Zheng H, Kang B, Kim H (2007) An ontology-based Bayesian network approach for representing uncertainty in clinical practice guidelines.\n                      Proc. 3rd Internat. Conf. Uncertainty Reasoning Semantic Web (Busan, Republic of Korea)\n                      , vol. 327 , 85\u201396."}],"container-title":["Information Systems Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/isre.2024.1071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:46:33Z","timestamp":1775144793000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/isre.2024.1071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":69,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1287\/isre.2024.1071"],"URL":"https:\/\/doi.org\/10.1287\/isre.2024.1071","relation":{},"ISSN":["1047-7047","1526-5536"],"issn-type":[{"value":"1047-7047","type":"print"},{"value":"1526-5536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}