{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:22:04Z","timestamp":1793132524714,"version":"4.5.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003467","name":"Hangzhou Dianzi University","doi-asserted-by":"publisher","award":["YBJG202524"],"award-info":[{"award-number":["YBJG202524"]}],"id":[{"id":"10.13039\/501100003467","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003467","name":"Hangzhou Dianzi University","doi-asserted-by":"publisher","award":["2024GH101"],"award-info":[{"award-number":["2024GH101"]}],"id":[{"id":"10.13039\/501100003467","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Mental health issues among university students are becoming increasingly prominent, making an accurate and efficient mental state monitoring system a critical challenge in higher education management. Existing intelligent screening approaches mostly rely on single-modality data and are not tailored to counselor-student dialogue records or structured background information. Consequently, current systems struggle to provide reliable early warnings for high-risk students, especially under highly imbalanced risk-level distributions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study develops a multimodal deep learning model, BCL (BERT-CNN-LASSO), which integrates counselor-student dialogue text with static background features (e.g., cumulative GPA, number of failed courses, financial aid status) to classify students into four ordered mental health risk levels for early warning. The model was evaluated on a curated real-world dataset of 600 university students collected from a counseling management system. BCL employs a BERT-based encoder for text representation, a dual-path CNN architecture for multi-scale feature extraction, and LASSO-based selection of static variables to enhance robustness under highly imbalanced risk distributions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the four-level mental health risk classification task, BCL achieved an overall accuracy of 0.752. At the category level, the model attained an accuracy of 0.897 for the highest-risk group (Level 1) and 0.967 for the lowest-risk group (Level 4), while maintaining a recall of 0.731 for Level 1, thereby reducing missed high-risk cases and limiting false alarms for low-risk students.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Comparative experiments demonstrate that each core component of BCL contributes to performance gains. These findings indicate that the proposed multimodal approach is a promising technical solution for intelligent early warning of university students' mental health problems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1679030","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T05:43:19Z","timestamp":1780551799000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A multimodal deep learning approach for mental health classification of university students: an intelligent early warning system"],"prefix":"10.3389","volume":"9","author":[{"given":"Fu","family":"Li","sequence":"first","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Mental Health Education Center, Zhejiang Chinese Medical University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxiao","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"183952","DOI":"10.1109\/ACCESS.2020.3029154","article-title":"Application of machine learning methods in mental health detection: a systematic review","volume":"8","author":"Abd Rahman","year":"2020","journal-title":"IEEE Access"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, cnn architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"B3","doi-asserted-by":"publisher","first-page":"676","DOI":"10.3390\/electronics11050676","article-title":"Deep learning for depression detection from textual data","volume":"11","author":"Amanat","year":"2022","journal-title":"Electronics"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1002\/jee.20574","article-title":"Mental health and wellbeing of undergraduate students in engineering: a systematic literature review","volume":"113","author":"Asghar","year":"2024","journal-title":"J. Eng. Educ"},{"key":"B5","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1007\/s11920-022-01387-4","article-title":"Public health approaches to promoting university students' mental health: a global perspective","volume":"24","author":"Bantjes","year":"2022","journal-title":"Curr. Psychiatry Rep"},{"key":"B6","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1080\/09638237.2018.1470319","article-title":"Student mental health: some answers and more questions","volume":"27","author":"Brown","year":"2018","journal-title":"J. Ment. Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jaac.2020.08.466","article-title":"Impact of covid-19 pandemic on college student mental health and wellness","volume":"60","author":"Copeland","year":"2021","journal-title":"J. Am. Acad. Child Adolesc. Psychiatry"},{"key":"B8","doi-asserted-by":"crossref","first-page":"106","DOI":"10.18653\/v1\/W16-0311","article-title":"\u201cExploratory analysis of social media prior to a suicide attempt,\u201d","volume-title":"Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology","author":"Coppersmith","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e18","DOI":"10.1017\/S0033291724003295","article-title":"Artificial intelligence in mental health care: a systematic review of diagnosis, monitoring, and intervention applications","volume":"55","author":"Cruz-Gonzalez","year":"2025","journal-title":"Psychol. Med"},{"key":"B10","first-page":"494","article-title":"\u201cA multi-model ensemble approach for proactive student mental health assessment,\u201d","volume-title":"in 2024 IEEE International Conference for Women in Innovation, Technology and Entrepreneurship","author":"Dayananda","year":"2024"},{"key":"B11","first-page":"2098","article-title":"\u201cDiscovering shifts to suicidal ideation from mental health content in social media,\u201d","volume-title":"in Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems","author":"De Choudhury","year":"2016"},{"key":"B12","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1186\/s12888-025-06483-2","article-title":"The application of artificial intelligence in the field of mental health: a systematic review","volume":"25","author":"Dehbozorgi","year":"2025","journal-title":"BMC Psychiatry"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e2301","DOI":"10.7717\/peerj-cs.2301","article-title":"A novel multi-model feature generation technique for suicide detection","volume":"10","author":"Ding","year":"2024","journal-title":"Peer J. Comput. Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e1782","DOI":"10.1002\/mpr.1782","article-title":"Barriers of mental health treatment utilization among first-year college students: first cross-national results from the who world mental health international college student initiative","volume":"28","author":"Ebert","year":"2019","journal-title":"Int. J. Methods Psychiatr. Res"},{"key":"B15","doi-asserted-by":"publisher","first-page":"052029","DOI":"10.1088\/1742-6596\/1486\/5\/052029","article-title":"Research on the identification of college students' mental health problems based on campus big data","volume":"1486","author":"Ge","year":"2020","journal-title":"J. Phys.: Conf. Ser"},{"key":"B16","doi-asserted-by":"publisher","first-page":"70370","DOI":"10.1109\/ACCESS.2022.3187502","article-title":"Multimodal educational data fusion for students' mental health detection","volume":"10","author":"Guo","year":"2022","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e267","DOI":"10.2196\/jmir.7023","article-title":"Application of synchronous text-based dialogue systems in mental health interventions: systematic review","volume":"19","author":"Hoermann","year":"2017","journal-title":"J. Med. Internet Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1037\/a0025957","article-title":"Mental health literacy: empowering the community to take action for better mental health","volume":"67","author":"Jorm","year":"2012","journal-title":"Am. Psychol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.32604\/iasc.2023.033360","article-title":"Deep learning for depression detection using twitter data","volume":"36","author":"Khafaga","year":"2023","journal-title":"Intell. Autom. Soft Comput"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1615788","DOI":"10.3389\/fdata.2025.1615788","article-title":"Analyzing student mental health with roberta-large: a sentiment analysis and data analytics approach","volume":"8","author":"Khan","year":"2025","journal-title":"Front. Big Data"},{"key":"B21","doi-asserted-by":"publisher","first-page":"6348681","DOI":"10.1155\/2022\/6348681","article-title":"Research on psychological emotion recognition of college students based on deep learning","volume":"2022","author":"Li","year":"2022","journal-title":"Sci. Programm"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/TKDE.2017.2686382","article-title":"Detecting stress based on social interactions in social networks","volume":"29","author":"Lin","year":"2017","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B23","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1109\/ECICE59523.2023.10383046","article-title":"\u201cResearch on construction of a model for detecting and warning psychological abnormalities in college students based on support vector machine classifier,\u201d","volume-title":"2023 IEEE 5th Eurasia Conference on IOT, Communication and Engineering (ECICE)","author":"Liu","year":"2023"},{"key":"B24","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1109\/ICIPCA61593.2024.10708980","article-title":"\u201cResearch on mental health problem identification algorithm of college students,\u201d","volume-title":"2024 IEEE 2nd International Conference on Image Processing and Computer Applications (ICIPCA)","author":"Luo","year":"2024"},{"key":"B25","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","article-title":"Principal components analysis (pca)","volume":"19","author":"Ma\u0107kiewicz","year":"1993","journal-title":"Comput. Geosci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e17450179315688","DOI":"10.2174\/0117450179315688240607052117","article-title":"Machine learning techniques to predict mental health diagnoses: a systematic literature review","volume":"20","author":"Madububambachu","year":"2024","journal-title":"Clin. Pract. Epidemiol. Mental Health: CP EMH"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-017-0431-4","article-title":"Frequency of data extraction errors and methods to increase data extraction quality: a methodological review","volume":"17","author":"Mathes","year":"2017","journal-title":"BMC Med. Res. Methodol"},{"key":"B28","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/978-3-030-45442-5_33","article-title":"\u201cUtilizing temporal psycholinguistic cues for suicidal intent estimation,\u201d","volume-title":"Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14-17, 2020, Proceedings, Part II 42","author":"Mathur","year":"2020"},{"key":"B29","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1136\/ebmental-2020-300180","article-title":"Digital phenotyping for mental health of college students: a clinical review","volume":"23","author":"Melcher","year":"2020","journal-title":"BMJ Ment Health"},{"key":"B30","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1176\/appi.ps.201600541","article-title":"Three problems with current digital mental health research... and three things we can do about them","volume":"68","author":"Mohr","year":"2017","journal-title":"Psychiatr. Serv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"9843","DOI":"10.1073\/pnas.1702155114","article-title":"Empathy and well-being correlate with centrality in different social networks","volume":"114","author":"Morelli","year":"2017","journal-title":"Proc. Nat. Acad. Sci. U. S. A"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.10095","article-title":"Cognitive-mental-llm: evaluating reasoning in large language models for mental health prediction via online text","author":"Patil","year":"2025","journal-title":"arXiv preprint arXiv:2503.10095"},{"key":"B33","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1609\/icwsm.v5i1.14137","article-title":"\u201cYou are what you tweet: analyzing twitter for public health,\u201d","author":"Paul","year":"2011","journal-title":"PProceedings of the International AAAI Conference on Web and Social Media"},{"key":"B34","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s40596-014-0205-9","article-title":"College students: mental health problems and treatment considerations","volume":"39","author":"Pedrelli","year":"2015","journal-title":"Acad. Psychiatry"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1002\/bjs.10895","article-title":"Lasso regression","volume":"105","author":"Ranstam","year":"2018","journal-title":"J. Br. Surg"},{"key":"B36","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.jad.2021.03.054","article-title":"Prevalence and risk factors for mental health problems in university undergraduate students: a systematic review with meta-analysis","volume":"287","author":"Sheldon","year":"2021","journal-title":"J. Affect. Disord"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3422824","article-title":"Using social media for mental health surveillance: a review","volume":"53","author":"Skaik","year":"2020","journal-title":"ACM Comput. Surv"},{"key":"B38","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.ipm.2016.06.009","article-title":"Tensistrength: stress and relaxation magnitude detection for social media texts","volume":"53","author":"Thelwall","year":"2017","journal-title":"Inform. Process. Manag"},{"key":"B39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/2632048.2632054","article-title":"\u201cStudentlife: assessing mental health, academic performance and behavioral trends of college students using smartphones,\u201d","author":"Wang","year":"2014","journal-title":"Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing"},{"key":"B40","doi-asserted-by":"publisher","first-page":"990235","DOI":"10.3389\/fpubh.2022.990235","article-title":"A measurement method for mental health based on dynamic multimodal feature recognition","volume":"10","author":"Xu","year":"2022","journal-title":"Front. Public Health"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1679030\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T05:43:22Z","timestamp":1780551802000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1679030\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":40,"alternative-id":["10.3389\/frai.2026.1679030"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1679030","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"article-number":"1679030"}}