SentimentCareBot: Retrieval-Augmented Generation Chatbot for Mental Health Support with Sentiment Analysis
Bibliographic record
Abstract
The global mental healthcare system faces various challenges in terms of accessibility and the availability of specialist support, such as psychologists and counselors, especially following the COVID-19 pandemic. This study explores a potential solution to this problem by developing a chatbot model, SentimentCareBot, which integrates sentiment analysis with retrieved-augmented generation (RAG) techniques and Large Language Models (LLMs). The study uses a public Mental Health Counseling Conversations Dataset and baseline selection methods such as Naive RAG, Multi-query RAG, and Hypothetical Document Embeddings (HyDE) to improve query translations. The findings from Tukey's Honest Significant Difference (HSD) test reveals a significant improvement in sentiment analysis performance when it is applied to the Multi-query RAG using the MistralAI language model, compared to both Multi-query RAG using the OpenAI language model and HyDE using OpenAI with Sentiment Analysis. These results demonstrate the potential of sentiment analysis to enhance the effectiveness of mental health chatbots.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".