RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews

Satpreet Harcharan Singh, Kevin Jiang, Kanchan Bhasin, Ashutosh Sabharwal, Nidal Moukaddam, Ankit Patel


Abstract
Semi-structured interviews (SSIs) are a commonly employed data-collection method in healthcare research, offering in-depth qualitative insights into subject experiences. Despite their value, manual analysis of SSIs is notoriously time-consuming and labor-intensive, in part due to the difficulty of extracting and categorizing emotional responses, and challenges in scaling human evaluation for large populations. In this study, we develop RACER, a Large Language Model (LLM) based expert-guided automated pipeline that efficiently converts raw interview transcripts into insightful domain-relevant themes and sub-themes. We used RACER to analyze SSIs conducted with 93 healthcare professionals and trainees to assess the broad personal and professional mental health impacts of the COVID-19 crisis. RACER achieves moderately high agreement with two human evaluators (72%), which approaches the human inter-rater agreement (77%). Interestingly, LLMs and humans struggle with similar content involving nuanced emotional, ambivalent/dialectical, and psychological statements. Our study highlights the opportunities and challenges in using LLMs to improve research efficiency and opens new avenues for scalable analysis of SSIs in healthcare research.
Anthology ID:
2024.nlp4science-1.8
Volume:
Proceedings of the 1st Workshop on NLP for Science (NLP4Science)
Month:
November
Year:
2024
Address:
Miami, FL, USA
Editors:
Lotem Peled-Cohen, Nitay Calderon, Shir Lissak, Roi Reichart
Venue:
NLP4Science
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
73–98
Language:
URL:
https://aclanthology.org/2024.nlp4science-1.8
DOI:
Bibkey:
Cite (ACL):
Satpreet Harcharan Singh, Kevin Jiang, Kanchan Bhasin, Ashutosh Sabharwal, Nidal Moukaddam, and Ankit Patel. 2024. RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews. In Proceedings of the 1st Workshop on NLP for Science (NLP4Science), pages 73–98, Miami, FL, USA. Association for Computational Linguistics.
Cite (Informal):
RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews (Singh et al., NLP4Science 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlp4science-1.8.pdf