Cited by 669Complex Network Analysis TechniquesOpinion Dynamics and Social InfluenceComplex Systems and Time Series Analysis

The “majority illusion” in social networks

Open access
Lerman, Kristina, Yan, Xiaoran, Wu, Xin-Zeng·2016·PLOS ONE

Abstract

Individual's decisions, from what product to buy to whether to engage in risky behavior, often depend on the choices, behaviors, or states of other people. People, however, rarely have global knowledge of the states of others, but must estimate them from the local observations of their social contacts. Network structure can significantly distort individual's local observations. Under some conditions, a state that is globally rare in a network may be dramatically over-represented in the local neighborhoods of many individuals. This effect, which we call the "majority illusion," leads individuals to systematically overestimate the prevalence of that state, which may accelerate the spread of social contagions. We develop a statistical model that quantifies this effect and validate it with measurements in synthetic and real-world networks. We show that the illusion is exacerbated in networks with a heterogeneous degree distribution and disassortative structure.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0147617

Cites

49 of 50 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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?

  • Homophily can systematically bias the perceptions of networked users, resulting in under- or over-estimations of the prevalence of user attributes within a population.

    “homophily—the tendency of similar people to interact and connect (McPherson et al., 2001)—can systematically bias the perceptions of networked users, resulting in under- or over-estimations of the prevalence of user attributes within a population”

    From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Lerman et al., 2016

    The Introduction and Conclusion (pages not provided) say that homophily exposes people to a biased sample of the population and can lead them to overestimate the prevalence of their own attributes. They do not describe homophily causing underestimation of attribute prevalence, so that part of the claim is not supported by our copy. (LLM, conf=0.83)

    Experimental — accuracy not yet measured
  • On social platforms, linking biases may result in systematically biased perceptions about users or content.

    “On social platforms, they may also result in systematically biased perceptions about users or content”

    From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Lerman et al., 2016

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 51 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. [7]Valente TW. Network Models of the Diffusion of Innovations (Quantitative Methods in Communication Subseries). Hampton Press (NJ); 1995.
  2. [44]Latané B, Darley JM. Bystander ‘Apathy’. American Scientist. 1969; 57(2): 244– 268. 5797312

Cited by

Sorted by citations

Authors
Lerman, K., Yan, X., & Wu, X.-Z.
Affiliations
University of Southern California (US)
Corresponding author
Lerman, Kristina
Venue
PLOS ONE
Published
2016-02-17
Volume
11
Issue
2
Pages
e0147617
ISSN
1932-6203 (ISSN-L)
OpenAlex
W1552468722
Cited by
669
References
51
Citations by year
2026: 11 · 2025: 13 · 2024: 15 · 2023: 26 · 2022: 22 · 2021: 135 · 2020: 123 · 2019: 119 · 2018: 94 · 2017: 78 · 2016: 30 · 2015: 3
FWCI
60.61
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
  • National Science Foundation (1217605)
  • Defense Advanced Research Projects Agency (W911NF- 12-1-0034)
  • Advanced Research Projects Agency
  • Air Force Office of Scientific Research (FA9550-, FA9550-10-1-, FA9550-10-1-0569)
Topics
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Opinion Dynamics and Social Influence
  • Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Complex Systems and Time Series Analysis
Keywords
social networks, prevalence estimation, social contagion, network structure, degree heterogeneity, disassortative mixing, statistical models
MeSH terms
Humans, Illusions, Normal Distribution, Social Networking

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