A multimodal deep learning approach for mental health classification of university students: an intelligent early warning system
Fu Li, Lei Wang, Wei Chen, Jian Zhang, Ying Huang, Chengxiao Jiang · 2026
Read A multimodal deep learning approach for mental health classification of university students: an intelligent early warning system by Fu Li, Lei Wang, Wei Chen, Jian Zhang, Ying Huang, Chengxiao Jiang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13275644.txt.
Description
Fu Li and co-authors present a 2026 deep learning system for flagging student mental health risk. University counselling services need earlier warnings, yet most tools use one data type alone. Their model combines counsellor dialogue records with background facts such as grades and financial aid.
The system, called BCL, reads dialogue with a BERT encoder and extracts patterns through a dual-path network. Background variables were trimmed with LASSO selection to keep the model robust. Tested on 600 students across four ordered risk levels, it reached an overall accuracy near three quarters. It caught the highest-risk group well while rarely mislabelling the lowest-risk students.
Catalog record
| CREATOR | Fu Li, Lei Wang, Wei Chen, Jian Zhang, Ying Huang, Chengxiao Jiang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |