MétaCan
Menu
Back to cohort
Record W7106712149 · doi:10.1155/hbe2/9942295

A Systematic Review on Mental Health Chatbots: Trends, Design Principles, Evaluation Methods, and Future Research Agenda

2025· article· en· W7106712149 on OpenAlexaff

Bibliographic record

VenueHuman Behavior and Emerging Technologies · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsUniversity of Alberta
FundersZayed University
KeywordsMental healthCognitionAdaptation (eye)Cognitive reframingSystematic reviewModality (human–computer interaction)Cognitive therapy

Abstract

fetched live from OpenAlex

Recent decades have witnessed a rise in the prevalence of common mental health problems coupled with an increasing demand for talk‐based psychological therapies. This has coincided with the rise of mental health chatbots (MHCs), a corollary of which is the use of MHCs, AI‐driven, conversational agents, to provide interactive support, guidance, and therapeutic engagement for persons experiencing mental health challenges. There has been a growing research interest in MHCs, and this study provides a much‐needed systematic review that examines this expanding research literature, identifying themes, trends, and areas worthy of further exploration. This review identified and systematically explored 97 published papers on MHCs. Most studies explored MHC design and evaluation, emphasizing empathy‐based chatbots and their relative efficacy compared with conventional delivery modes (e.g., in‐person human therapists). Text‐based communication was the most frequently utilized modality over and above the use of audio, graphical, or mixed modes. The most commonly used therapeutic orientation among MHCs was cognitive behavioral therapy (CBT), with far less focus on third‐wave evidence‐based approaches such as dialectical behavior therapy and acceptance and commitment therapy. The most frequently targeted mental health condition was depression, although there were several other conditions also considered. Most MHC research has not considered cultural appropriateness or cultural adaptation of interventions. Further, limited attention to severe or high‐risk symptomatology has been given. Meanwhile, we noted that most of the studies used quantitative and mixed evaluation methods. Evaluation shows persistent challenges around personalization, privacy, and technical reliability. Future research should focus on integrating human‐in‐the‐loop mechanisms, advancing cultural adaptation, incorporating thought‐challenging CBT techniques, embedding ethics into design, and exploring large language models (LLMs) for more adaptive and empathetic support.

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 imitation

Not 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.

metaresearch head score (Codex)0.066
metaresearch head score (Gemma)0.194
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Systematic review · Consensus signal: Systematic review
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.066
Threshold uncertainty score0.348

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0660.194
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0110.010
Bibliometrics0.0210.021
Science and technology studies0.0010.002
Scholarly communication0.0070.007
Open science0.0030.003
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0060.001

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.

Opus teacher head0.322
GPT teacher head0.580
Teacher spread0.258 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSystematic review
Domainnot available
GenreReview

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueHuman Behavior and Emerging TechnologiesSame topicDigital Mental Health InterventionsFrench-language works237,207