Research foundations

Bristlenose's sentiment categories, the way it forms themes, and its codebooks are not invented for the product — each is drawn from established research. That is why they line up with methods and frameworks you may already use, and why the output can be checked against the literature rather than taken on trust. This is the short version; the full reference list, with citations, is in Academic sources.

The sentiment taxonomy

The seven sentiments — frustration, confusion, doubt, surprise, satisfaction, delight, confidence — are drawn from emotion science and affective computing. They were chosen to capture the states that matter in a research interview without over-specifying. See Sentiment and signals for how they are applied.

The analysis method

Themes are produced inductively — they emerge from the data rather than being matched against a fixed list — following the reflexive thematic-analysis approach of Braun and Clarke. Quotes are edited for readability without changing their meaning, on a principle of dignity without distortion: a participant should sound like themselves on a good day, never different.

The codebook frameworks

The optional codebooks come from named user-experience and user-research authorities — Norman, Nielsen, Garrett, Morville, and Yablonski. The Laws of UX codebook in particular rests on primary cognitive-psychology sources: Hick (1952) on decision time, Fitts (1954) on target acquisition, Miller (1956) on working-memory limits, Kahneman and colleagues (1993) on the peak-end rule, and the Gestalt school on perception. See Codebook frameworks for what each contributes.

Full citations

See Academic sources for the complete reference list, grouped into emotion science, user-experience research, trust and credibility, usability heuristics, cognitive psychology, qualitative research methods, and affective computing.