Clinical Efficacy, Therapeutic Mechanisms, and Implementation Features of Cognitive Behavioral Therapy–Based Chatbots for Depression and Anxiety: Narrative Review
Bibliographic record
Abstract
Background: Cognitive behavioral therapy (CBT)-based chatbots, many of which incorporate artificial intelligence (AI) techniques, such as natural language processing and machine learning, are increasingly evaluated as scalable solutions for addressing mental health issues, such as depression and anxiety. These fully automated or minimally supported interventions offer novel pathways for psychological support, especially for individuals with limited access to traditional therapy. Objective: This narrative review synthesized evidence on the clinical efficacy, therapeutic mechanisms, and technological features of CBT-based chatbots designed to alleviate depressive and anxiety symptoms. Methods: Fourteen peer-reviewed studies published between January 2015 and March 2025 were identified through systematic searches and met predefined inclusion criteria. The studies were analyzed to extract information on intervention structure, therapeutic components, outcomes, and implementation characteristics. Results: Across the included studies, CBT-based chatbots consistently demonstrated short-term reductions in depressive symptoms, whereas findings for anxiety outcomes were mixed, with some studies reporting improvements and others showing nonsignificant or unreported effects. Moderate effect sizes were observed for depression. Reported therapeutic features included cognitive restructuring, behavioral activation, relaxation and mindfulness strategies, emotional support, self-monitoring and feedback, and therapeutic alliance. Technological characteristics such as real-time feedback and adaptive goal tracking were associated with enhanced engagement and adherence. Conclusions: CBT-based chatbots appear to be a promising and scalable modality for delivering psychological support, particularly for underserved populations. However, variability in study designs, heterogeneity of outcome reporting, and limited long-term evidence pose challenges for generalizability. Emerging evidence from generative AI chatbots (eg, Therabot and Limbic Care) highlights both opportunities and risks. Future work should examine long-term efficacy, adaptive personalization, cross-cultural adaptation, and rigorous ethical oversight.
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 | 0.005 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".