Enhancing Access to Health Information for Adolescent Girls in Bangladesh Through a Culturally Responsive AI Chatbot
Bibliographic record
Abstract
The advancement of Large Language Models (LLMs) is leading to new possibilities in healthcare. This paper introduces a chatbot to support adolescent girls in Bangladesh who face cultural and social barriers in accessing sexual, reproductive, and mental health (SRMH) information. With smartphones and digital platforms becoming widespread, conversational agents can provide personalized health education and access to information but many existing tools fail to address the needs of linguistically diverse populations like Bengali speakers. Our research fills this gap by using language models and utilizing methods such as Retrieval-Augmented Generation (RAG) combined with keyword-based filters and LLM-based classifiers. Our chatbot caters to the cultural and language needs of Bengalispeaking female adolescents, especially focused on SRMH. Leveraging a clinically validated dataset, our chatbot achieves an overall accuracy of 72.5%, which is a 46.5% improvement over the baseline RAG method. Our findings show how LLMs can be used in healthcare education for teenage girls and highlight the need for model improvement and larger datasets. It's a step forward in using AI to promote women's health literacy in areas where information is scarce.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".