Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 49 of the 50 references it cites were found in a registry or an index.

TweepFake: About detecting deepfake tweets

Open access

Abstract

The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake . It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.

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 · 10.1371/journal.pone.0251415

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Architecture of the tested deep neural networks based on character encoding. Three different architectures were tested: a) a CNN sub-network using three different kernel sizes (3,4, and 5) combined together and followed by a dropout layer, b) a bidirectional GRU followed by a dropout layer, and c) a network exploiting both CNN and GRU to extract spatial and temporal features from data in order to try to improve the effectiveness of the solution.
Fig 1 Architecture of the tested deep neural networks based on character encoding. Three different architectures were tested: a) a CNN sub-network using three different kernel sizes (3,4, and 5) combined together and followed by a dropout layer, b) a bidirectional GRU followed by a dropout layer, and c) a network exploiting both CNN and GRU to extract spatial and temporal features from data in order to try to improve the effectiveness of the solution.CC BY · PubMed Central
Fig 2 Accuracy heat-map over fake account type.
Fig 2 Accuracy heat-map over fake account type.CC BY · PubMed Central

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

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?

3 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

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 50 references

Research works printed but not linked: 3

  1. R Gorwa, 2020, Special Issue:Cleaning Up Social Media, 225
  2. R Zellers, 2019, Advances in Neural Information Processing Systems, 9054
  3. Z Yang, 2019, Advances in Neural Information Processing Systems, 5754

Cited by

See all 196

Metadata

Authors
Fagni, T., Falchi, F., Gambini, M., Martella, A., & Tesconi, M.
Affiliations
  • Institute of Informatics and Telematics (IT)
  • Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
  • University of Pisa (IT)
  • University of Trento (IT)
Corresponding author
Falchi, Fabrizio
Venue
PLOS ONE
Published
2021-05-13
Volume
16
Issue
5
Pages
e0251415
ISSN
1932-6203 (ISSN-L)
OpenAlex
W3046357466
Cited by
185
References
50
Citations by year
2026: 24 · 2025: 45 · 2024: 50 · 2023: 40 · 2022: 18 · 2021: 7
FWCI
39.82
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion)
  • Institutional Research Information System University of Turin (University of Turin) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • ISTI Open Portal (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
Horizon 2020 Framework Programme (871042, 95191)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
Keywords
deepfake detection, AI-generated text detection, social bots, Twitter, text generation models, GPT-2, Markov chains, recurrent neural networks, LSTM, bot detection
MeSH terms
Artificial Intelligence, Humans, Language, Markov Chains, Social Media

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: TweepFake: About detecting deepfake tweets. https://app.cochat.ai/papers/10.1371/journal.pone.0251415
The paper
Fagni, T., Falchi, F., Gambini, M., Martella, A., & Tesconi, M. (2021). TweepFake: About detecting deepfake tweets. PLOS ONE. https://doi.org/10.1371/journal.pone.0251415

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.