CoChat

Detection and Resolution of Rumours in Social Media: A Survey

Open access

The DOI matches its Crossref record; 197 of the 197 references it cites were found in a registry or an index; 52 of the 188 sources its claims cite were checked for support.

Abstract

Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e., items of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how to automatically assess their veracity, using natural language processing and data mining techniques. In this article, we introduce and discuss two types of rumours that circulate on social media: long-standing rumours that circulate for long periods of time, and newly emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification, and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far toward the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for the detection and resolution of rumours.

Overview

CoChat Summary

TL;DR

This survey reviews research on detecting and resolving rumours in social media, defining rumours as unverified at the time of posting and proposing a four-component rumour classification system: detection, tracking, stance classification, and veracity classification. It summarizes datasets, methods, applications, and open challenges, concluding that most work has focused on stance and veracity while detection and tracking remain underdeveloped.

Key findings

  • The paper defines a rumour as “an item of circulating information whose veracity status is yet to be verified at the time of posting” and distinguishes long-standing rumours from newly emerging rumours during breaking news.
  • It proposes a rumour classification architecture with four components: rumour detection, rumour tracking, rumour stance classification, and rumour veracity classification; most prior research has focused on the latter two.
  • Reported datasets include the PHEME dataset of rumours and non-rumours with 1,972 rumours and 3,830 non-rumours across 5 breaking news stories; the PHEME stance dataset covering nine events; RumourEval 2017 with over 300 rumours annotated as true, false, or unverified; and Kwon et al.’s dataset with 51 true rumours and 60 false rumours.
  • In stance analysis, Mendoza et al. studied 14 rumours (7 true, 7 false) and found over 95% of tweets associated with true rumours were “affirms,” while 38% of tweets associated with false rumours were “denies” and 17% were “questions.”

Methods

  • Survey/literature review of computational approaches to social media rumours, organized around data collection and annotation, rumour characterization, the four-component classification architecture, applications, and future research directions.
  • Reviews datasets, features, classifiers, and evaluation practices from prior studies; no new empirical data collection or experiments are reported.
  • Synthesizes reported results and identifies state-of-the-art approaches, including Zubiaga et al. (2017) for rumour detection, Hamidian and Diab (2015) for rumour tracking, Kochkina et al. (2017) and later Aker et al. (2017) for stance classification, and Enayet and El-Beltagy (2017) for veracity classification in RumourEval.

Limitations

  • The paper states that lack of publicly available datasets has been an important limitation and encourages researchers to release their own datasets.
  • The paper states that most work has focused on stance and veracity classification, while rumour detection and tracking are understudied; tracking of newly emerging rumours has not yet been studied, and generalisability across events remains difficult.
  • Evident from the text: as a survey, it does not present new experiments or a unified benchmark, and the paper itself notes that state-of-the-art comparisons are difficult because studies use different datasets and evaluation methods.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1145/3161603

Cites

197 of 197 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

47 Valid · 2 Not valid · 90 Not checked · 93 Own results and interpretations

46 more claims · 3 with their cited sources checked

Create a free account to see all 232 claims and to verify the 4 references still open.

See all claims — free account
  • It may state two separate claims as one. 106
  • Probably not a substantial claim. 136
  • The quote only partly states this claim. 3

Create a free account to see these claims.

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?

Citations

Cites

Research works printed but not linked: 45

  1. Gordon, 1947, Allport and Leo Postman
  2. Babakar Mevan, 2016, The state of automated factchecking. Full Fact
  3. 10.5555/3191835.3192014 · doi:10.5555/3191835.3192014
  4. Chang Cheng, Advanced Data Mining and Applications: 12th International Conference, ADMA 2016, Gold Coast, QLD, Australia, December 12-15, 2016, Proceedings. Springer, 751--763
  5. Alton Y., Proceedings of the International MultiConference of Engineers and Computer Scientists, 1
  6. 10.5555/3192424.3192572 · doi:10.5555/3192424.3192572
  7. Declerck Thierry, 2015, Proceedings of the Workshop on Social Media and the Web of Linked Data. Springer, 3--17
  8. Derczynski Leon, 2014, UMAP Workshops.
  9. Enayet Omar, 2017, El-Beltagy
  10. Finn Samantha, 2014, Eni Mustafaraj, Megan O'Keefe, Lindsay Tang, Susan Tang, and Laura Zeng.
  11. Lozano Marianela García, 2017, Proceedings of SemEval. ACL.
  12. Giasemidis Georgios, International Conference on Social Informatics. Springer, 185--205
  13. Guo Weiwei, 2012, Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers., 1
  14. Hamidian Sardar, Proceedings of the 5th International Conference on Social Media Technologies, Communication, and Informatics (SOTICS’15)
  15. Hamidian Sardar, 2016, Diab
  16. Hannak Aniko, 2014, Proceedings of the AAAI Conference on Weblogs and Social Media.
  17. Hassan Naeemul, 2015, Proceedings of the Computation and Journalism Symposium, NYC, NY.
  18. Hunt Elle, 2016, What is fake news? How to spot it and what you can do to stop it. The Guardian (December
  19. Jo Dong-Gi, 2002, Diffusion of rumors on the internet, Inform. Soc. Rev., 2002, 77
  20. Kwon Sejeong, 2014, Proceedings of the International Conference on Weblogs and Social Media (ICWSM). AAAI, 650--651
  21. Lazer David, 2009, Lada Adamic, Sinan Aral, Albert Laszlo Barabasi, Devon Brewer, Nicholas Christakis, Noshir Contractor, James Fowler, Myron Gutmann, et al.
  22. Lendvai Piroska, 2016, Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC)
  23. Lendvai Piroska, Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics. 31--40
  24. Lendvai Piroska, Joint Proceedings of the Posters and Demos Track of the 12th International Conference on Semantic Systems (SEMANTiCS’16) and the 1st International Workshop on Semantic Change 8 Evolving Semantics
  25. 10.5555/2035562.2035636 · doi:10.5555/2035562.2035636
  26. Qazvinian Vahed, 2011, Proceedings of EMNLP. 1589--1599
  27. Resnick Paul, 2014, Proceedings of the Computational Journalism Conference.
  28. 10.1145/2870630 · DOI
  29. Rosnow Ralph L., 2005, Foster
  30. Sayyadi Hassan, 2009, Proceedings of the AAAI Conference on Weblogs and Social Media.
  31. Serrano Emilio, Comput. Collect. Intell
  32. Silverman Craig, Verification Handbook
  33. Silverman Craig, How News Websites Spread (and Debunk) Online Rumors, Unverified Claims and Misinformation
  34. Silverman Craig, Verification Handbook for Investigative Reporting: A Guide to Online Search and Research Techniques for Using UGC and Open Source Information in Investigations
  35. Singh Vikram, 2017, Asif Ekbal, and Pushpak Bhattacharya.
  36. 10.5555/1687878.1687912 · doi:10.5555/1687878.1687912
  37. Starbird Kate, 2014, Mason
  38. Tolosi Laura, 2016, Proceedings of the ICWSM Workshop on Social Media in the Newsroom.
  39. Trottier Daniel, Revolutions, Riots, Crime and Policing in the Age of Facebook, Twitter and YouTube
  40. Wang Wen, 2011, Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers, 2
  41. Wardle Claire, 2017, Fake news. It’s complicated. First Draft News (February
  42. Wu Ke, Proceedings of the 2015 IEEE 31st International Conference on Data Engineering. IEEE, 651--662
  43. Zeng Li, Proceedings of the Tenth International AAAI Conference on Web and Social Media. AAAI, 747--750
  44. Zubiaga Arkaitz, 2016, Proceedings of the 26th International Conference on Computational Linguistics. Association for Computational Linguistics, 2438--2448
  45. Zubiaga Arkaitz, 2016, Geraldine Wong Sak Hoi, and Peter Tolmie

Cited by

See all 862

Metadata

Authors
Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., & Procter, R.
Affiliations
  • University of Warwick (GB)
  • University of Duisburg-Essen (DE)
  • University of Sheffield (GB)
Venue
ACM Computing Surveys
Published
2018-02-20
Volume
51
Issue
2
Pages
1-36
ISSN
  • 0360-0300 (ISSN-L)
  • 1557-7341
OpenAlex
W3125491592
Cited by
862
References
193
Citations by year
2026: 67 · 2025: 105 · 2024: 78 · 2023: 93 · 2022: 120 · 2021: 131 · 2020: 108 · 2019: 101 · 2018: 45
FWCI
173.84
Type
journal article
Language
en
Open access
Locations
  • ACM Computing Surveys (publishedVersion, cc-by)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Warwick Research Archive Portal (University of Warwick) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • COMRADES H2020 Project (687847)
  • Alan Turing Institute
  • PHEME FP7 Project (611233)
  • EPSRC Career Acceleration Fellowship (EP/I004327/1)
  • SoBigData Research Infrastructure (654024)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
Keywords
rumor detection, social media, breaking news, misinformation

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (prompt extract-v3).

A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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

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.