Thematic analysis as interaction model and research method
What if we modeled human-AI interaction on thematic analysis rather than conversation? And what if we used that same method to discover themes in a knowledge garden?
Thematic analysis as interaction model and research method
Note from Maaike: âI actually made a typo here, I didnât mean thematic analysis as interaction model, but research method. But now Claude suggested an interaction model that actually opens up new ideas for my âhow to replace conversation as a metaphorâ. Discover might be an interesting verb to explore.â
As a research method
In thematic analysis, you work through data iteratively: reading, coding, grouping, refining themes, going back to check. With a large enough context window, an AI can ingest an entire content base in one go. What would be a good method to discover existing and emerging themes across all that content? Thematic analysis is a conventional, well-researched method for exactly that.
As an interaction model
What if the interaction between a person and an AI isnât a conversation, but a research process?
Youâre not having a conversation, youâre doing collaborative analysis. The AI reads, you direct. It proposes patterns, you accept or redirect. The unit of work isnât a turn, itâs a theme. The verb isnât âtalkâ or âchatâ, itâs âdiscoverâ.
Connects to is-conversation-still-a-useful-metaphor and the note-taking/metacognition metaphors explored there.