CoChat
Sign Up
Cited by 859Misinformation and Its ImpactsComplex Network Analysis TechniquesSpam and Phishing Detection

Prominent Features of Rumor Propagation in Online Social Media

Kwon, Sejeong, Cha, Meeyoung, Jung, Kyomin, Chen, Wei, Wang, Yajun·2013·2013 IEEE 13th International Conference on Data Mining
DOI 10.1109/icdm.2013.61
Open this paper in CoChat — free account

Abstract

The problem of identifying rumors is of practical importance especially in online social networks, since information can diffuse more rapidly and widely than the offline counterpart. In this paper, we identify characteristics of rumors by examining the following three aspects of diffusion: temporal, structural, and linguistic. For the temporal characteristics, we propose a new periodic time series model that considers daily and external shock cycles, where the model demonstrates that rumor likely have fluctuations over time. We also identify key structural and linguistic differences in the spread of rumors and non-rumors. Our selected features classify rumors with high precision and recall in the range of 87% to 92%, that is higher than other states of the arts on rumor classification.

Integrity signals

Registry

Crossref · 10.1109/icdm.2013.61

Cites

1 of 1 references verified0 citation errors · 0 not checkable

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?

  • Rumour popularity tends to fluctuate over time on social media and other internet platforms, but may be discussed again after popularity fades.

    “Other studies looking at temporal patterns of rumours have suggested that their popularity tends to fluctuate over time in social media (Kwon et al. 2013;Kwon and Cha 2014;Lukasik et al. 2015b) and other platforms on the internet (Jo 2002), but with a possibility of being discussed again later in time after rumour popularity fades.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Kwon et al. 2013

  • Kwon et al. (2013) showed that combining significant features identified by random forest with baseline features led to performance degradation.

    “The authors also showed that a combination of significant features identified by random forest and baseline features led to performance degradation.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Kwon et al. (2013)

  • Kwon et al. (2013) proposed temporal, structural, and linguistic feature categories.

    “Kwon et al. (2013) proposed a new set of feature categories: temporal, structural, and linguistic.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Kwon et al. (2013)

  • Kwon et al. (2013) found random forest performed best for both feature selection and classification, while SVM performed best with baseline features from Castillo et al. (2011).

    “The results showed that for both selection of significant features and subsequent classification, a random forest classifier performed best.The best results using the baseline features adopted from Castillo et al. (2011) were obtained using an SVM.”

    From Detection and Resolution of Rumours in Social Media (2019) · cites this paper as Kwon et al. (2013)

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Kwon, S., Cha, M., Jung, K., Chen, W., & Wang, Y.
Affiliations
  • Korea Advanced Institute of Science and Technology (KR)
  • Seoul National University (KR)
  • Microsoft Research Asia (China) (CN)
ORCID
Venue
2013 IEEE 13th International Conference on Data Mining
Publisher
IEEE
Published
2013-12
Pages
1103-1108
ISSN
1550-4786 (ISSN-L)
DOI
10.1109/icdm.2013.61
OpenAlex
W2032897813
Cited by
859
References
1
Citations by year
2026: 25 · 2025: 52 · 2024: 74 · 2023: 98 · 2022: 116 · 2021: 145 · 2020: 109 · 2019: 86 · 2018: 60 · 2017: 43 · 2016: 24 · 2015: 23 · 2014: 4
FWCI
52.07
Type
conference paper
Language
en
Open access
closed
Locations
Proceedings (publishedVersion)
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
rumor propagation, rumor detection, social networking sites, rumor classification, structural features, linguistic features, information dissemination

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