CorpusStudio: Surfacing Emergent Patterns in a Corpus of Prior Work while Writing

2025-03-16

AI Summary

Addressing the challenge of identifying and applying implicit community norms in academic writing, this paper proposes a corpus-driven real-time writing assistance method. The approach employs statistical modeling, context-sensitive sentence retrieval, and keyword frequency analysis to automatically uncover domain-specific section-level structural distributions and syntactic patterns; it further operationalizes corpus-level statistical distributions into an interactive, visual writing interface. This work introduces the novel paradigm of “norm operationalization,” enabling authors to instantaneously perceive, emulate, and adapt linguistic and structural conventions during composition. A user study (N=16) demonstrates that participants significantly improved manuscript organization and rhetorical strategies, and reported substantially increased confidence in both norm adherence and principled innovation.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

Many communities, including the scientific community, develop implicit writing norms. Understanding them is crucial for effective communication with that community. Writers gradually develop an implicit understanding of norms by reading papers and receiving feedback on their writing. However, it is difficult to both externalize this knowledge and apply it to one's own writing. We propose two new writing support concepts that reify document and sentence-level patterns in a given text corpus: (1) an ordered distribution over section titles and (2) given the user's draft and cursor location, many retrieved contextually relevant sentences. Recurring words in the latter are algorithmically highlighted to help users see any emergent norms. Study results (N=16) show that participants revised the structure and content using these concepts, gaining confidence in aligning with or breaking norms after reviewing many examples. These results demonstrate the value of reifying distributions over other authors' writing choices during the writing process.

Problem

• Identify implicit writing norms in scientific communities
• Externalize and apply writing norms to personal writing
• Support writers in aligning with or breaking norms effectively

Innovation

• Ordered distribution over section titles
• Retrieved contextually relevant sentences
• Algorithmically highlighted recurring words