How a Stylistic, Machine-Generated Thesaurus Impacts a Writer's Process
Open accessAbstract
Writers regularly use a thesaurus to help them write well; the thesaurus is one of the few widespread writing support tools and many writers find it integral to their writing practice. A normal thesaurus is hand-crafted and structured around strict synonymy for a given word sense. However, writers rarely look for a perfectly synonymous word -- instead they have additional ideas or constraints, such as words that are less cliche, more specific, or less gendered. Poets describe their usage as searching for words that "hold more interesting connotations." We present a machine learning approach to thesaurus generation, using word embeddings, that leverages stylistically distinct corpora -- such as naturalist writing, novels by a particular author, or writing from a technical discipline. We show examples of how stylistic thesauruses differ from each other and from a regular thesaurus, as well as preliminary responses from two writers who are given multiple stylistic thesauruses. Writers describe these thesauruses as reflective of style, unique from each other, and more exploratory and associative than a regular thesaurus. They also describe an increased attention to connotation. We outline plans for quantitative evaluation of stylistic thesauruses, and user studies to understand their impact on specific tasks.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI reduces creative workloads by providing valuable suggestions and refining content for professional use, thereby helping writers overcome creative blocks.
“Prior studies have shown that AI reduces creative workloads by providing valuable suggestions [10, 33] and refining content for professional use [26, 43, 83], thereby helping writers overcome creative blocks.”
From Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation (2025) · cites this paper as [33]
The Conclusion and future work section reports that two writers found the machine-generated thesaurus results inspiring, supporting the claim that AI can provide useful suggestions. The paper does not establish that those suggestions reduce creative workloads or help writers overcome creative blocks. The separate claim about refining content for professional use is attached to other citations in the citing sentence. (LLM, conf=0.84)
Experimental — accuracy not yet measuredThe lack of significant AI impact on professional writers' quality may suggest that professional writers already possess well-honed skills that AI cannot readily augment.
“This could suggest that professional writers already possess wellhoned skills that AI cannot readily augment [27].”
From Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models (2024) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 11 · Cited by 32
Research works printed but not linked: 3
- Richard P Gabriel, Jilin Chen, and Jeffrey Nichols. 2015. InkWell: A Creative Writer's Creative Assistant. In Proceedings of the 2015 ACM SIGCHI Conference on Creativity and Cognition. ACM, 93-102.
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013). · arXiv
- MW Van Someren, YF Barnard, and JAC Sandberg. 1994. The think aloud method: a practical approach to modelling cognitive. Citeseer, Chapter 3.
- Authors
- Gero, K. I., & Chilton, L. B.
- Affiliations
- Columbia University (US)
- Venue
- Proceedings of the 2019 on Creativity and Cognition
- Publisher
- ACM
- Published
- 2019-06-13
- Pages
- 597-603
- OpenAlex
- W2949543916
- Cited by
- 32
- References
- 11
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 11 · 2023: 1 · 2022: 5 · 2021: 3
- FWCI
- 0.77
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Creativity and Cognition (publishedVersion)
- Funders
- National Science Foundation (NSF GRF (DGE - 1644869))
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Arts and Humanities › Literature and Literary Theory › Digital Humanities and Scholarship
- Keywords
- writing support tools, word embeddings, connotation, synonymy (linguistics), technical writing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
