Cited by 583Misinformation and Its ImpactsComplex Network Analysis TechniquesSpam and Phishing Detection

Enquiring Minds: Early Detection of Rumors in Social Media from Enquiry Posts

Zhao, Zhe, Resnick, Paul, Mei, Qiaozhu·2015·Proceedings of the 24th International Conference on World Wide Web

Abstract

Many previous techniques identify trending topics in social media, even topics that are not pre-defined. We present a technique to identify trending rumors, which we define as topics that include disputed factual claims. Putting aside any attempt to assess whether the rumors are true or false, it is valuable to identify trending rumors as early as possible. It is extremely difficult to accurately classify whether every individual post is or is not making a disputed factual claim. We are able to identify trending rumors by recasting the problem as finding entire clusters of posts whose topic is a disputed factual claim.

Integrity signals

Registry

Crossref · 10.1145/2736277.2741637

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • A rumour detection system that flags early postings with uncertain veracity can warn users that the information may be false.

    “A rumour detection system that identifies, in its early stages, postings whose veracity status is uncertain, can be effectively used to warn users that the information in them may turn out to be false”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Zhao et al. 2015

  • The first work to tackle detection of new rumours was by Zhao et al. (2015).

    “The first work that tackled the detection of new rumours is that by Zhao et al. (2015).”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Zhao et al. 2015

  • Zhao et al.'s approach assumes rumours provoke tweets from skeptical users questioning veracity; a piece of information with enquiring tweets is then considered rumourous.

    “Their approach builds on the assumption that rumours will provoke tweets from skeptic users who question or enquire about their veracity; the fact that a piece of information has a number of enquiring tweets associated would then imply that the information is rumourous.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Zhao et al. 2015

  • Zhao et al. could not evaluate by recall and instead evaluated only by precision.

    “It was not viable for them to evaluate by recall, and instead only evaluated by precision.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Zhao et al. 2015

  • Zhao et al. created a manually curated list of five regular expressions to identify enquiring tweets, clustered them by similarity, and deemed each cluster a candidate rumour.

    “The authors created a manually curated list of five regular expressions (e.g.,”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Zhao et al. 2015

No citation lists for this paper

No citation lists for this paper yet — checked again daily.

References 43 · Cited by 583

Authors
Zhao, Z., Resnick, P., & Mei, Q.
Affiliations
University of Michigan (US)
Venue
Proceedings of the 24th International Conference on World Wide Web
Published
2015-05-18
Pages
1395-1405
OpenAlex
W1638051351
Cited by
583
References
43
Citations by year
2026: 8 · 2025: 34 · 2024: 35 · 2023: 44 · 2022: 54 · 2021: 103 · 2020: 85 · 2019: 95 · 2018: 54 · 2017: 44 · 2016: 23 · 2015: 4
FWCI
152.99
Type
conference paper
Language
en
Open access
closed
Locations
International World Wide Web Conference (WWW) (publishedVersion)
Funders
  • DARPA (W911NF-12-1-0037)
  • National Science Foundation (IIS-1054199, IIS-0968489)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
  • Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
Keywords
trending topics, rumors, social media, topic extraction, rumor detection

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