PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 5, 20260 citations

From transcript to insights: Summarizing safety culture interviews with LLMs

View Full Paper
WSW. SteijnJLJanneke van de LooDBDolf van der Beek

Key Points

  • The research seeks to evaluate how AI, specifically the OpenAI o1-model, can aid in summarizing safety culture interviews.
  • Utilized the OpenAI o1-model for summarizing interview transcripts
  • Conducted qualitative analysis on safety culture interviews
  • Assessed efficiency and accuracy of AI-generated summaries
  • AI-generated summaries improved the efficiency of interviewers
  • Reports were concise and followed a pre-defined format
  • Some inaccuracies (hallucinations) were identified in generated summaries

Abstract

The latest developments in AI have the potential to significantly support qualitative analysis of interview transcripts. This study explores the utility of the OpenAI o1-model to assist in efficiently obtaining reliable summarizations of safety culture interviews. Analysis shows that the current approach has the clear potential to significantly improve efficiency of interviewers by providing a concise report that summarizes multiple interviews according to a pre-defined format. However, some hallucinations are present in the generated report. Additional work will aim at reducing their presence, but such hallucinations also emphasizes that LLMs should primarily assist, rather than replace, interviewers in creating a definitive report.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Steijn et al. (2025) studied this question.

synapsesocial.com/papers/698434ebf1d9ada3c1fb3a9ehttps://doi.org/10.1051/matecconf/202541303003/pdf
Ask AI
Helpful
Bookmark
Share
View Full Paper