Towards Cognitive Process-Aware Proactive Writing Support
2026-08-31 • Human-Computer Interaction
Human-Computer InteractionArtificial Intelligence
AI summaryⓘ
The authors studied how computers can help people write by guessing what kind of help is needed without the user having to explain. They used a theory about the thinking steps in writing to figure out what support fits each step. They created a tool called AToM CoWriter that watches how people write and suggests helpful tips at the right times. Their tests showed this method helps writers explore ideas better and makes them more interested in the suggestions. Overall, the authors show that understanding writing processes can make smart writing helpers more useful.
Large language modelsCreative writingProactive supportCognitive process theory of writingFlower and Hayes modelWriting interactionsSupport selectionUser engagement
Authors
Masahiro Yoshida, Atsuya Kobayashi, Kei Tateno, Xiang 'Anthony' Chen
Abstract
Large language models can support writing, but existing tools require users to explicitly articulate prompts-particularly burdensome in creative writing, where intentions are often ambiguous. Proactive support that infers users' needs from writing interactions could alleviate this burden, but raises two challenges: determining what support to provide and when to intervene. This work focuses on the former. We hypothesize that Flower and Hayes' cognitive process theory of writing-which characterizes writing through six cognitive processes-offers an interpretable bridge between observable writing behavior and appropriate support types. Through a formative study and literature review, we identify 14 writing support types associated with these cognitive processes, along with characteristic interaction behaviors linked to each process. We then instantiate this framework in AToM CoWriter, which infers support needs from writing interactions and document context. Two within-subjects studies (N = 21) provide initial evidence that this approach improves expressiveness and idea exploration, and that cognitive process inference increases engagement with proactive suggestions. These findings suggest that cognitive processes can provide a promising basis for support selection in proactive writing systems.