This study investigates whether ChatGPT can be used as a secondary coder to assist in analyzing interview transcripts in deductive qualitative research, using content analysis with a predefined coding scheme. Interview coding is a crucial but time- and resource-intensive step in qualitative research. With the rise of Generative Artificial Intelligence (GenAI), this study explores if ChatGPT can assist in this task in a reliable, efficient, and responsible way.

To do so, the paper presents a step-by-step methodology for implementing ChatGPT as a secondary coder, using filtered interview transcripts and a predefined coding scheme. The study compares ChatGPT’s coding performance with that of a human secondary coder. Data was collected through semi-structured interviews with accounting students. First, the primary researcher manually analyzed the data using a deductive approach. Next, a second human researcher and ChatGPT (ChatGPT-4o Plus) were appointed as secondary coders to independently verify and validate the coding.

Results show that ChatGPT reaches over 99% agreement with human coders after a structured discussion phase. The use of ChatGPT reduces coding time and costs, while enabling constructive, iterative conversations about coding disagreements. The paper also offers detailed prompts, practical guidelines, and critical reflections to help researchers implement this methodology responsibly.

This paper informs researchers about the potential of GenAI in qualitative research by demonstrating ChatGPT’s potential to assist in coding interviews transcripts. Practical tools for integrating GenAI into the qualitative research process are provided.