A Case Study on Assessing AI Assistant Competence in Narrative Interviews
Open Access
- 4 October 2024
- journal article
- case study
- Published by F1000 Research Ltd in F1000Research
- Vol. 13, 601
Abstract
* Background Researchers are leading the development of AI designed to conduct interviews. These developments imply that AI's role is expanding from mere data analysis to becoming a tool for social researchers to interact with and comprehend their subjects. Yet, academic discussions have not addressed the potential impacts of AI on narrative interviews. In narrative interviews, the method of collecting data is a collaborative effort. The interviewer also contributes to exploring and shaping the interviewee's story. A compelling narrative interviewer has to display critical skills, such as maintaining a specific questioning order, showing empathy, and helping participants delve into and build their own stories. Methods This case study configured an OpenAI Assistant on WhatsApp to conduct narrative interviews with a human participant. The participant shared the same story in two distinct conversations: first, following a standard cycle and answering questions earnestly, and second, deliberately sidetracking the assistant from the main interview path as instructed by the researcher, to test how well the metrics could reflect the deliberate differences between different conversations. The AI's performance was evaluated through conversation analysis and specific narrative indicators, focusing on its adherence to the interview structure, empathy, narrative coherence, complexity, and support for human participant agency. The study sought to answer these questions: 1) How can the proposed metrics help us, as social researchers without a technical background, understand the quality of the AI-driven interviews in this study? 2) What do these findings contribute to our discussion on using AI in narrative interviews for social research? 3) What further research could these results inspire? Results The findings show to what extent the AI maintained structure and adaptability in conversations, illustrating its potential to support personalized, flexible narrative interviews based on specific needs. Conclusions These results suggest that social researchers without a technical background can use observation-based metrics to gauge how well an AI assistant conducts narrative interviews. They also prompt reflection on AI's role in narrative interviews and spark further research.Keywords
This publication has 52 references indexed in Scilit:
- Autoethnography as a research method for educational technology: a reflective discourseEducational Technology Research and Development, 2023
- Measuring perceived empathy in dialogue systemsAI & SOCIETY, 2023
- Using AI chatbots to provide self-help depression interventions for university students: A randomized trial of effectivenessInternet Interventions, 2022
- Future directions for chatbot research: an interdisciplinary research agendaComputing, 2021
- Survey on psychotherapy chatbotsConcurrency and Computation: Practice and Experience, 2020
- Survey on evaluation methods for dialogue systemsArtificial Intelligence Review, 2020
- Applications of Artificial Intelligence Methodologies to Behavioral and Social SciencesJournal of Child and Family Studies, 2019
- An Exploratory Investigation of the Counseling Competencies Scale: A Measure of Counseling Skills, Dispositions, and BehaviorsCounselor Education and Supervision, 2012
- What is an affordance and can it help us understand the use of ICT in education?Education and Information Technologies, 2009
- A Sequential Analysis of Externalizing in Narrative Therapy with ChildrenContemporary Family Therapy, 2009