Assessing the Reliability of Large Language Models for Deductive Qualitative Coding: A Comparative Intervention Study with ChatGPT
Published in ASIS&T Annual Meeting Proceedings, 2025
Abstract
Evaluates whether LLMs can reliably perform deductive qualitative coding protocols, highlighting accuracy baselines and failure modes.
Recommended citation: Hila, Angelin, & Hauser, Elliott. (2025). "Assessing the Reliability of Large Language Models for Deductive Qualitative Coding: A Comparative Intervention Study with ChatGPT." ASIS&T Annual Meeting Proceedings.
Download Paper