Utilizing User Preferences in Designing the AGILE (Accelerating Access to Gender-Based Violence Information and Services Leveraging on Technology Enhanced) Chatbot

Anne Ngũnjiri; Peter Memiah; Robert Kimathi; Fernando A Wagner; Annrita Ikahu; Eunice Omanga; Emmanuel Kweyu; Carol Ngunu; Lilian Otiso

doi:10.3390/ijerph20217018

Utilizing User Preferences in Designing the AGILE (Accelerating Access to Gender-Based Violence Information and Services Leveraging on Technology Enhanced) Chatbot

Int J Environ Res Public Health. 2023 Nov 3;20(21):7018. doi: 10.3390/ijerph20217018.

Authors

Anne Ngũnjiri¹, Peter Memiah², Robert Kimathi¹, Fernando A Wagner³, Annrita Ikahu¹, Eunice Omanga¹, Emmanuel Kweyu⁴, Carol Ngunu⁵, Lilian Otiso¹

Affiliations

¹ LVCT Health Kenya, Nairobi P.O. Box 19835-00202, Kenya.
² Graduate School, University of Maryland, 620 W. Lexington Street, Baltimore, MD 21201, USA.
³ School of Social Work, University of Maryland, 525 W. Redwood Street, Baltimore, MD 21201, USA.
⁴ Faculty of Information Technology, Strathmore University, Nairobi P.O. Box 59857-00200, Kenya.
⁵ Department of Health, Nairobi City County, Nairobi P.O. Box 30075-00100, Kenya.

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.

Keywords: adolescent health; chatbot; violence.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adolescent
Artificial Intelligence
Female
Gender-Based Violence* / psychology
Humans
Male
Sexual Behavior
Technology
Violence

Grants and funding

The study received funding from Grand Challenges Canada, Funding Number R-ST-POC-2206-53899. Therefore, the views presented do not reflect the views of the funding agency.