Utilizing User Preferences in Designing the AGILE (Accelerating Access to Gender-Based Violence Information and Services Leveraging on Technology Enhanced) Chatbot
Bibliographic record
Abstract
INTRODUCTION: Technology advancements have enhanced artificial intelligence, leading to a user shift towards virtual assistants, but a human-centered approach is needed to assess for acceptability and effectiveness. The AGILE chatbot is designed in Kenya with features to redefine the response towards gender-based violence (GBV) among vulnerable populations, including adolescents, young women and men, and sexual and gender minorities, to offer accurate and reliable information among users. METHODS: We conducted an exploratory qualitative study through focus group discussions (FGDs) targeting 150 participants sampled from vulnerable categories; adolescent girls and boys, young women, young men, and sexual and gender minorities. The FGDs included multiple inquiries to assess knowledge and prior interaction with intelligent conversational assistants to inform the user-centric development of a decision-supportive chatbot and a pilot of the chatbot prototype. Each focus group comprised 9-10 members, and the discussions lasted about two hours to gain qualitative user insights and experiences. We used thematic analysis and drew on grounded theory to analyze the data. RESULTS: The analysis resulted in 14 salient themes composed of sexual violence, physical violence, emotional violence, intimate partner violence, female genital mutilation, sexual reproductive health, mental health, help-seeking behaviors/where to seek support, who to talk to, and what information they would like, features of the chatbot, access of chatbot, abuse and HIV, family and community conflicts, and information for self-care. CONCLUSION: Adopting a human-centered approach in designing an effective chatbot with as many human features as possible is crucial in increasing utilization, addressing the gaps presented by marginalized/vulnerable populations, and reducing the current GBV epidemic by moving prevention and response services closer to people in need.
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 | 0.011 | 0.021 |
| 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 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".