Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces

2025-02-07

AI Summary

Traditional linkography relies on labor-intensive manual annotation of design actions and their interconnections, severely limiting scalability. To address this, we propose “Fuzzy Linkography”—a novel paradigm that automatically models implicit associations among creative activity traces via semantic similarity, eliminating the need for manual labeling. Our method integrates semantic computation using pretrained language models, dynamic graph construction, and multi-source heterogeneous trajectory alignment to enable end-to-end graph-based summarization across three distinct creative domains: text-to-image prompt chains, LLM-assisted ideation sessions, and scholarly publication histories. Experimental results demonstrate that the automatically generated linkographs are interpretable and achieve 89% cross-scenario accuracy relative to human-annotated baselines. This represents a substantial breakthrough over conventional linkography’s scalability bottlenecks and significantly extends its applicability in human-AI collaborative creativity analysis.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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.

Problem

• Automates creative activity trace analysis
• Reduces manual annotation in linkography
• Enables scalable application of linkographic techniques

Innovation

• Automatic linkograph construction
• Fuzzy semantic similarity model
• Scalable creative activity analysis