Applications of AI-powered Conversational Chatbot for Mental Health
Bibliographic record
Abstract
Psychological issues have become a pervasive problem affecting the quality of life for many individuals. However, the scarcity of professional psychotherapists and the high threshold for receiving human psychological counselling prevent most people from obtaining timely, high-quality psychological help. To address this issue, chatbots have been developed to participate in the promotion of public mental health. Empowered by Artificial Intelligence (AI), especially Large Language Models (LLMs), chatbots have the potential to revolutionize the field of mental health by offering personalized and full-time support. Moreover, AI-powered chatbots can assist researchers in collecting more data to understand mental health better and develop more effective treatments. This paper categorizes and summarizes the recent applications of conversational chatbot technology in the mental health field, including human-robot relationships, the use of conversational chatbots with mental health tasks in counselling and online settings, the generation of counselling dialogue data, and the evaluation of datasets and models. The advantages and disadvantages of these technologies are explored, along with the current technical shortcomings of conversational chatbots. Additionally, the challenges to their widespread adoption and use, as well as future directions for development, are discussed.
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 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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.
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".