Can AI generate qualitative data for software engineering research?
Presented by Marco Gerosa, School of Informatics, Computing, and Cyber Systems
Qualitative research is extensively used to understand human factors in software engineering, but it faces significant challenges in recruiting participants. Large language models (LLMs) have demonstrated strong capabilities in generating human-like text, raising questions about whether they can augment or serve as surrogates for human participants in certain qualitative research contexts. In this talk, we discuss situations where AI can and cannot mimic human behavior.
