Intelligent vulnerability assessment system for college students mental health based on few-sample reinforcement learning approach
Xiaobo Huang, Jiayue Ji, Shi Cheng · 2026
Read Intelligent vulnerability assessment system for college students mental health based on few-sample reinforcement learning approach by Xiaobo Huang, Jiayue Ji, Shi Cheng (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/PMC13651551.txt.
Description
Xiaobo Huang and two colleagues design a system that judges college students' mental health vulnerability from very few labeled examples and tracks risk as it evolves. Labeled data are scarce, labeling is costly, privacy is sensitive, and samples skew heavily. Older tools give one static judgment that cannot follow a changing student.
Their grading model borrows meta-learning methods that recognize new categories from a few examples. It assigns risk grades through prototype matching with ordered thresholds. A second method frames monitoring as a sequence of decisions learned by a meta-reinforcement policy. Tests used simulated cohorts rather than real students. Grading accuracy beat a deep classifier by a wide margin at ten examples per grade. The decision policy flagged risk more precisely than its non-meta rival without degenerating into escalation. The authors present the pair as a practical route to earlier screening where labeled data are scarce.
Catalog record
| CREATOR | Xiaobo Huang, Jiayue Ji, Shi Cheng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 123 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |