Effect of a Cognitive Behavioral Therapy–Based AI Chatbot on Depression and Loneliness in Chinese University Students: Randomized Controlled Trial With Financial Stress Moderation
Bibliographic record
Abstract
Background: Mental health concerns are prevalent among university students, with financial stress further compounding these issues. While cognitive behavioral therapy (CBT) is effective for these conditions, its delivery through artificial intelligence (AI) chatbots represents a promising approach, especially in non-Western contexts. Objective: This study aims to investigate the efficacy of a culturally adapted, CBT-based AI chatbot for improving the well-being of Chinese university students and to examine whether financial stress moderates its effectiveness. Methods: In this randomized controlled trial, 100 university students (mean age 20.8, SD 2.2 years; 62/100, 62% female) were allocated to either an intervention (n=50) or a waitlist control group (n=50). The intervention group interacted with a CBT-based AI chatbot for 7 consecutive days. Depression (Center for Epidemiologic Studies Depression Scale), anxiety (Generalized Anxiety Disorder-7 scale), and loneliness (UCLA Loneliness Scale) were assessed at baseline, day 3, and day 7. Financial stress was measured using the Psychological Inventory of Financial Scarcity. Results: Significant group×time interactions were found for depression (F2,196=8.63; P<.001; η²p=.08) and loneliness (F2,196=5.57; P=.004; η²p=.05), but not for anxiety (F2,196=1.31; P=.27; η²p=.01). Post hoc comparisons showed significant reductions in both depression (t=3.85; P<.001) and loneliness (t=4.28; P<.001) from baseline to postintervention in the intervention group, with corresponding effect sizes of Cohen d=0.71 (95% CI 0.30-1.12) and Cohen d=0.60 (95% CI 0.20-1.00), respectively. No significant changes were observed in the waitlist control group. Exploratory subgroup analyses revealed that participants with high financial stress demonstrated significantly greater improvements in depression (F2,52=11.56; P<.001; η²p=.31) and loneliness (F2,52=11.18; P<.001; η²p=.30) compared to those with low financial stress. Conclusions: The culturally adapted, CBT-based AI chatbot effectively reduced depression and loneliness in Chinese university students, with stronger effects among those experiencing high financial stress. These findings highlight the potential of AI-driven interventions to provide accessible mental health support, particularly for financially stressed students.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".