Machine Intelligence and Human Intelligence: Exploring the Potentials of Machine Learning Based Approaches to Qualitative Survey Data Analysis

This paper aims to explore new methods for qualitative data analysis in the digital age. We applied three machine learning (ML)-based methods—topic modelling via LDA and BERTopic, and generative AI-assisted inductive coding—in conjunction with the conventional thematic analysis method, to a set of qualitative data collected from a student survey over four years at a Canadian engineering school. The analysis processes as well as the outputs generated from the four methods were compared and evaluated against the trustworthiness criteria for quality in qualitative research. We observe that the ML-based approaches to analyzing qualitative survey data offer some levels of credibility and transferability while dependability and confirmability vary by method; and human intelligence of researchers needs to be involved to enhance the quality of ML-based analysis. Moving forward, we recommend a human-AI collaborative approach that combines ML-based inductive coding and human intelligence-based deductive coding processes. This new approach can facilitate and accelerate qualitative research and foster cross-disciplinary collaboration in qualitative data analysis.