Antipatterns in AI-assisted Qualitative Data Analysis: A Catalog of Temptations and Pitfalls for Software Engineering Researchers

Summary

Senior qualitative methodologists catalogue antipatterns in AI-assisted qualitative data analysis, grouped by escalating impact into Dangerous Drivers, Operational Missteps and Analytical Failures, explicitly so that reviewers gain vocabulary for calling out failed practice and the field avoids accelerated production of low-quality research. Aimed at software engineering but the failure modes transfer directly to qualitative and interpretive IS work. Concrete methodological guidance rather than general exhortation.

Contribution

Queued — not yet read.

Method

Queued — not yet read.

Relevance to RISE

Surfaced by the 2026-09-07 literature sweep as a medium-priority candidate for the RISE knowledge base (angle: human–AI research collaboration). Verified against: Opened https://arxiv.org/abs/2608.27927, read full abstract, 4 authors, 2026-08-28, cs.SE/cs.AI. Dedupe: no 'antipatterns' or 'qualitative data analysis' match.

Critique / open questions

Queued — not yet assessed.

Key quotes

AI-assisted qualitative data analysis (QDA) offers unprecedented opportunities to streamline software engineering (SE) research, yet uncritical use risks compromising analytical rigor and flooding the field with accelerated production of low-quality research. (abstract)

While tactical best practices will naturally evolve over time, SE researchers currently lack strategic guidance to identify and mitigate methodological risks when attempting AI-assisted QDA. (abstract)