Determining an author's native language by mining a text for errors
Abstract
In this paper, we show that stylistic text features can be exploited to determine an anonymous author's native language with high accuracy. Specifically, we first use automatic tools to ascertain frequencies of various stylistic idiosyncrasies in a text. These frequencies then serve as features for support vector machines that learn to classify texts according to author native language.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Current authorship attribution models struggle with out-of-distribution issues when faced with languages and LLMs not encountered during training, leading to decreased accuracy and reliability.
“Current authorship attribution models also struggle with out-ofdistribution issues when faced with languages and LLMs not encountered during training, leading to decreased accuracy and reliability [Koppel et al., 2005;Wu et al., 2023b].”
From Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges (2025) · cites this paper as Koppel et al., 2005
Cited by
Sorted by citations
Computational methods in authorship attribution
Koppel, M., Schler, J., & Argamon, S. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20961 · Cited by 528 · see citing works
Self-citationAutomatically profiling the author of an anonymous text
Argamon, S., Koppel, M., Pennebaker, J. W., & Schler, J. (2009) · Communications of the ACM · doi:10.1145/1461928.1461959 · Cited by 376 · see citing works
Self-citationAuthorship Attribution for Social Media Forensics
Rocha, A., Scheirer, W. J., Forstall, C. W., Cavalcante, T., Theophilo, A., Shen, B., Carvalho, A. R. B., & Stamatatos, E. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2603960 · Cited by 222 · see citing works
Multi modal decision fusion for continuous authentication
Fridman, L., Stolerman, A., Acharya, S., Brennan, P., Juola, P., Greenstadt, R., & Kam, M. (2015) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2014.10.018 · Cited by 64 · see citing works
Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
Huang, B., Chen, C., & Shu, K. (2025) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3715073.3715076 · Cited by 42 · see citing works
“Current authorship attri-bution models also struggle with out-of-distribution issues when faced with languages and LLMs not encountered during training, leading to decreased accuracy and reliability (Koppel et al., 2005, Wu et al., 2023b).”
- Authors
- Koppel, M., Schler, J., & Zigdon, K.
- Affiliations
- Bar-Ilan University (IL)
- ORCID
- Schler, Jonathan
- Venue
- Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
- Publisher
- ACM
- Published
- 2005-08-21
- Pages
- 624-628
- OpenAlex
- W2135528482
- Cited by
- 167
- References
- 0
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 3 · 2023: 5 · 2022: 6 · 2021: 6 · 2020: 17 · 2019: 6 · 2018: 12 · 2017: 17 · 2016: 9 · 2015: 16 · 2014: 16 · 2013: 22 · 2012: 15
- FWCI
- 1.19
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
- Keywords
- stylometry, stylistic features, text mining, authorship analysis, support vector machine, text classification
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
