Michael K. Paasche-Orlow

arXiv2026

Designing for Adolescent Voice in Health Decisions: Embodied Conversational Agents for HPV Vaccination

Adolescents are directly affected by preventive health decisions such as vaccination, yet their perspectives are rarely solicited or supported. Most digital interventions for Human Papillomavirus (HPV) vaccination are designed exclusively for parents, implicitly treating adolescents as passive recipients rather than stakeholders with agency. We present the design and evaluation of a mobile intervention that gives adolescents a voice in HPV vaccination decisions alongside their parents. The system uses embodied conversational agents tailored to each audience: parents interact with an animated physician using education and motivational interviewing techniques, while adolescents can choose between an age-appropriate doctor or a narrative fantasy game that conveys HPV facts through play. We report findings from a clinic-based pilot study with 21 parent-adolescent dyads. Results indicate high satisfaction across both audiences, improved HPV knowledge, and increased intent to vaccinate. We discuss design implications for supporting adolescent participation, choice, and agency in decisions about their health.

cs.HC↗

arXiv2024

Keeping Users Engaged During Repeated Administration of the Same Questionnaire: Using Large Language Models to Reliably Diversify Questions

Standardized, validated questionnaires are vital tools in research and healthcare, offering dependable self-report data. Prior work has revealed that virtual agent-administered questionnaires are almost equivalent to self-administered ones in an electronic form. Despite being an engaging method, repeated use of virtual agent-administered questionnaires in longitudinal or pre-post studies can induce respondent fatigue, impacting data quality via response biases and decreased response rates. We propose using large language models (LLMs) to generate diverse questionnaire versions while retaining good psychometric properties. In a longitudinal study, participants interacted with our agent system and responded daily for two weeks to one of the following questionnaires: a standardized depression questionnaire, question variants generated by LLMs, or question variants accompanied by LLM-generated small talk. The responses were compared to a validated depression questionnaire. Psychometric testing revealed consistent covariation between the external criterion and focal measure administered across the three conditions, demonstrating the reliability and validity of the LLM-generated variants. Participants found that the variants were significantly less repetitive than repeated administrations of the same standardized questionnaire. Our findings highlight the potential of LLM-generated variants to invigorate agent-administered questionnaires and foster engagement and interest, without compromising their validity.

cs.HC↗