CoChat

Distinguishing academic science writing from humans or ChatGPT with over 99% accuracy using off-the-shelf machine learning tools

Open access
Desaire, Heather, Chua, Aleesa E., Isom, Madeline, Jarosova, Romana, Hua, David · 2023 · Cell Reports Physical Science
Cited by 110

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

ChatGPT has enabled access to artificial intelligence (AI)-generated writing for the masses, initiating a culture shift in the way people work, learn, and write. The need to discriminate human writing from AI is now both critical and urgent. Addressing this need, we report a method for discriminating text generated by ChatGPT from (human) academic scientists, relying on prevalent and accessible supervised classification methods. The approach uses new features for discriminating (these) humans from AI; as examples, scientists write long paragraphs and have a penchant for equivocal language, frequently using words like "but," "however," and "although." With a set of 20 features, we built a model that assigns the author, as human or AI, at over 99% accuracy. This strategy could be further adapted and developed by others with basic skills in supervised classification, enabling access to many highly accurate and targeted models for detecting AI usage in academic writing and beyond.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.xcrp.2023.101426

Cites

11 of 11 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 11 references

Research works printed but not linked: 5

  1. Leiter, 2023, ChatGPT: a meta-analysis after 2.5 months, arXiv
  2. Chrisinger, 2023, It’s not just our students – ChatGPT is coming for faculty writing, Chron. High Educ., 69, 13
  3. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V. R.BERT.: A robustly optimized bert pretraining approach. Preprint at arXiv. https://doi.org/10.48550/arXiv.1907.11692v1. · arXiv · doi:10.48550/arxiv.1907.11692v1
  4. Guo, 2023, How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection, arXiv
  5. Hua, 2021, Improved discrimination of disease states using proteomics data with the updated Aristotle classifier, J. Proteome Res., 20, 2823, 10.1021/acs.jproteome.1c00066 · DOI

Cited by

See all 110

Metadata

Authors
Desaire, H., Chua, A. E., Isom, M., Jarosova, R., & Hua, D.
Venue
Cell Reports Physical Science
Publisher
Elsevier BV
Published
2023-06
Volume
4
Issue
6
Pages
101426
ISSN
2666-3864 (ISSN-L)
OpenAlex
W4379741168
Cited by
110
References
11
FWCI
9.66
Type
journal article
Language
en
Open access
gold
Licence
Funders
  • National Institutes of Health (R35GM130354)
  • University of Kansas

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Distinguishing academic science writing from humans or ChatGPT with over 99% accuracy using off-the-shelf machine learning tools. https://app.cochat.ai/papers/10.1016/j.xcrp.2023.101426
The paper
Desaire, H., Chua, A. E., Isom, M., Jarosova, R., & Hua, D. (2023). Distinguishing academic science writing from humans or ChatGPT with over 99% accuracy using off-the-shelf machine learning tools. Cell Reports Physical Science. https://doi.org/10.1016/j.xcrp.2023.101426

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.