Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces
Abstract
Linkography -- the analysis of links between the design moves that make up an episode of creative ideation or design -- can be used for both visual and quantitative assessment of creative activity traces. Traditional linkography, however, is time-consuming, requiring a human coder to manually annotate both the design moves within an episode and the connections between them. As a result, linkography has not yet been much applied at scale. To address this limitation, we introduce fuzzy linkography: a means of automatically constructing a linkograph from a sequence of recorded design moves via a "fuzzy" computational model of semantic similarity, enabling wider deployment and new applications of linkographic techniques. We apply fuzzy linkography to three markedly different kinds of creative activity traces (text-to-image prompting journeys, LLM-supported ideation sessions, and researcher publication histories) and discuss our findings, as well as strengths, limitations, and potential future applications of our approach.
Keywords
Cite
@article{arxiv.2502.04599,
title = {Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces},
author = {Amy Smith and Barrett R. Anderson and Jasmine Tan Otto and Isaac Karth and Yuqian Sun and John Joon Young Chung and Melissa Roemmele and Max Kreminski},
journal= {arXiv preprint arXiv:2502.04599},
year = {2025}
}
Comments
ACM C&C 2025. Code available at https://github.com/mkremins/fuzzy-linkography