On pushing DeepFake Tweet Detection capabilities to the limits
Open accessAbstract
The recent advances in natural language generation provide an additional tool to manipulate public opinion on social media. Even though there has not been any report of malicious exploit of the newest generative techniques so far, disturbing human-like scholarly examples of GPT-2 and GPT-3 can be found on social media. Therefore, our paper investigates how the state-of-the-art deepfake social media text detectors perform at recognizing GPT-2 tweets as machine-written, also trying to improve the state-of-the-art by hyper-parameter tuning and ensembling the most promising detectors; finally, our work concentrates on studying the detectors’ capabilities to generalize over tweets generated by the more sophisticated and complex evolution of GPT-2, that is GPT-3. Results demonstrate that hyper-parameter optimization and ensembling advance the state-of-the-art, especially on the detection of GPT-2 tweets. However, all tested detectors dramatically decreased their accuracy on GPT-3 tweets. Despite this, we found out that even though GPT-3 tweets are much closer to human-written tweets than the ones produced by GPT-2, they still have latent features in common share with other generative techniques like GPT-2, RNN and other older methods. All things considered, the research community should quickly devise methods to detect GPT-3 social media texts, as well as older generative methods.
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?
Subsequent studies have built upon the Fagni et al. dataset to explore various strategies for bot detection based on content.
“Subsequent studies have built upon this dataset to explore various strategies for bot detection based on content (Saravani et al., 2021;Gambini et al., 2022;Tourille et al., 2022).”
From Anatomy of an AI-powered malicious social botnet (2024) · cites this paper as Gambini et al., 2022
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3019 · Cited by 470 · cited 1× · see citing works
“Theonly works that dealt with language distributional features were carried out by Badaskar et al. (2008) [3] and Gehrmann et al. (2019) [13], respectively.”
BackgroundThe Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race
Cresci, S., Di Pietro, R., Petrocchi, M., Spognardi, A., & Tesconi, M. (2017) · Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion · doi:10.1145/3041021.3055135 · Cited by 381 · see citing works
Self-citationTweepFake: about detecting deepfake tweets
Fagni, T., Falchi, F., Gambini, M., Martella, A., & Tesconi, M. (2021) · PLOS ONE · doi:10.1371/journal.pone.0251415 · Cited by 185 · see citing works
Self-citationAutomated Identification of Social Media Bots Using Deepfake Text Detection
Saravani, S. M., Ray, I., & Ray, I. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-92571-0_7 · Cited by 18 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Chao, L. S., & Wong, D. F. (2025) · Computational Linguistics · doi:10.1162/coli_a_00549 · Cited by 212 · see citing works
A Watermark for Large Language Models
Kirchenbauer, J., Geiping, J., Wen, Y., Katz, J., Miers, I., & Goldstein, T. (2023) · arXiv · doi:10.48550/arxiv.2301.10226 · Cited by 194 · see citing works
“However, detection approaches are slowly losing ground as LM capabilities increase, for example Gambini et al. (2022) note that a range of detection strategies for GPT-2 already struggle with GPT-3.”
Anatomy of an AI-powered malicious social botnet
Yang, K., & Menczer, F. (2024) · Journal of Quantitative Description: Digital Media · doi:10.51685/jqd.2024.icwsm.7 · Cited by 71 · 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
“…LLM-generated text is crucial for several applications, including combating misinformation and disinformation on social media (Chen and Shu, 2024b, Gambini et al., 2022, Stiff and Johansson, 2022), identifying spam (Jindal and Liu, 2008), preventing phishing attacks (Hazell, 2023), identifying…”
- Authors
- Gambini, M., Fagni, T., Falchi, F., & Tesconi, M.
- Affiliations
- Institute of Informatics and Telematics (IT)
- Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
- Venue
- 14th ACM Web Science Conference 2022
- Publisher
- ACM
- Published
- 2022-06-26
- Pages
- 154-163
- OpenAlex
- W4283461431
- Cited by
- 19
- References
- 6
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 5 · 2023: 8
- FWCI
- 2.21
- Type
- conference paper
- Language
- en
- Open access
- Locations
- ACM Web Science Conference (WebSci) (publishedVersion)
- ISTI Open Portal (submittedVersion, other-oa)
- Funders
- SoBigData++ (871042)
- AI4Media (95191)
- EU H2020 (INFRAIA-01-2018-2019)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Keywords
- deepfake detection, AI-generated text detection, GPT-2, GPT-3, social media text, hyperparameter optimization, ensemble learning, generative AI, public opinion manipulation
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
