CoChat
Sign Up
Cited by 4Recommender Systems and TechniquesComplex Network Analysis TechniquesMisinformation and Its Impacts

Evaluating Content Exposure Bias in Social Networks

Open access
Bartley, Nathan, Burghardt, Keith, Lerman, Kristina·2023·Proceedings of the International Conference on Advances in Social Networks Analysis and Mining
DOI 10.1145/3625007.3627724
Open this paper in CoChat — free accountOpen PDF

Abstract

Online social platforms employ personalized feed algorithms to gather and prioritize messages from accounts followed by users, which distorts content's perceived popularity prior to personalization. We call this "exposure bias," and our research focuses on quantifying it using diverse exposure bias metrics, and we evaluate recommendation algorithms through various content ranking heuristics. Similarly we simulate activity in a network to assess the influence of such ranking heuristics on exposure bias. Furthermore, we are working on agent-based model simulations to comprehend the impact of ranking schemes, with the ultimate goal of exploring intervention effects over time. Our empirical findings reveal that users exposed to popularity-based feeds experience significantly lower exposure bias compared to chronologically-ordered feeds.

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 · 10.1145/3625007.3627724

Cites

2 of 2 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?

  • Previous research has shown that popularity biases can lead to a skew in the visibility of tweets when comparing personalized feeds with reverse-chronological ones, and that users are disproportionately exposed to friends' tweets.

    “Previous research has shown that popularity biases can lead to a skew in the visibility of tweets when comparing personalized feeds with reverse-chronological ones, and that users are disproportionately exposed to friends' tweets [6,7].”

    From Auditing Political Exposure Bias: Algorithmic Amplification on Twitter/X During the 2024 U.S. Presidential Election (2025) · cites this paper as [7]

    RQ1 reports a skew in the popularity of tweets observed in personalized versus reverse-chronological feeds. The Introduction describes how highly active followed accounts can be overrepresented, but RQ1 says the eight-sockpuppet study did not identify a skew in exposure between the activity network and the feeds. The paper therefore does not establish the broader claim that users are disproportionately exposed to friends’ tweets. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Previous studies on algorithmic bias have reported amplification patterns within users' in-network content similar to the exposure inequality found in this study.

    “Our analysis of exposure inequality aligns with previous studies on algorithmic bias, which have reported similar amplification patterns within users' in-network content [7].”

    From Auditing Political Exposure Bias: Algorithmic Amplification on Twitter/X During the 2024 U.S. Presidential Election (2025) · cites this paper as [7]

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

Research works printed but not linked: 21

  1. M. S. Granovetter, "The strength of weak ties," American journal of sociology, vol. 78, no. 6, pp. 1360-1380, 1973.
  2. P. Panagiotopoulos, J. Barnett, A. Z. Bigdeli, and S. Sams, "Social media in emergency management: Twitter as a tool for communicating risks to the public," Technological Forecasting and Social Change, vol. 111, pp. 86-96, 2016. 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  3. D. Nikolov, A. Flammini, and F. Menczer, "Right and left, partisan- ship predicts (asymmetric) vulnerability to misinformation," Harvard Kennedy School (HKS) Misinformation Review, 2021.
  4. W. Chen, D. Pacheco, K.-C. Yang, and F. Menczer, "Neutral bots reveal political bias on social media," arXiv preprint arXiv:2005.08141, 2020. · arXiv
  5. N. Bartley, A. Abeliuk, E. Ferrara, and K. Lerman, "Auditing algorithmic bias on twitter," in 13th ACM Web Science Conference 2021, 2021, pp. 65-73.
  6. R. Kardosh, A. Y. Sklar, A. Goldstein, Y. Pertzov, and R. R. Hassin, "Minority salience and the overestimation of individuals from minor- ity groups in perception and memory," Proceedings of the National Academy of Sciences, vol. 119, no. 12, p. e2116884119, 2022.
  7. N. O. Hodas and K. Lerman, "The simple rules of social contagion," Scientific reports, vol. 4, no. 1, p. 4343, 2014.
  8. M. G. Rodriguez, K. Gummadi, and B. Schoelkopf, "Quantifying infor- mation overload in social media and its impact on social contagions," in Proceedings of the international AAAI conference on web and social media, vol. 8, no. 1, 2014, pp. 170-179.
  9. B. Mønsted, P. Sapieżyński, E. Ferrara, and S. Lehmann, "Evidence of complex contagion of information in social media: An experiment using twitter bots," PloS one, vol. 12, no. 9, p. e0184148, 2017.
  10. M. Los, Z. Christoff, and D. Grossi, "On the graph theory of majority illusions," arXiv preprint arXiv:2304.02258, 2023. · arXiv
  11. P. Juneja and T. Mitra, "Auditing e-commerce platforms for algorithmi- cally curated vaccine misinformation," in Proceedings of the 2021 chi conference on human factors in computing systems, 2021, pp. 1-27.
  12. C. Sandvig, K. Hamilton, K. Karahalios, and C. Langbort, "Auditing algorithms: Research methods for detecting discrimination on internet platforms," Data and discrimination: converting critical concerns into productive inquiry, vol. 22, no. 2014, pp. 4349-4357, 2014.
  13. J. Bandy and N. Diakopoulos, "More accounts, fewer links: How algorithmic curation impacts media exposure in twitter timelines," Proceedings of the ACM on Human-Computer Interaction, vol. 5, no. CSCW1, pp. 1-28, 2021.
  14. J. Angwin, J. Larson, S. Mattu, and L. Kirchner, "Machine bias," in Ethics of data and analytics. Auerbach Publications, 2016, pp. 254- 264.
  15. M. Tomlein, B. Pecher, J. Simko, I. Srba, R. Moro, E. Stefancova, M. Kompan, A. Hrckova, J. Podrouzek, and M. Bielikova, "An audit of misinformation filter bubbles on youtube: Bubble bursting and recent behavior changes," in Proceedings of the 15th ACM Conference on Recommender Systems, 2021, pp. 1-11.
  16. L. Beattie, D. Taber, and H. Cramer, "Challenges in translating research to practice for evaluating fairness and bias in recommendation systems," in Proceedings of the 16th ACM Conference on Recommender Systems, 2022, pp. 528-530.
  17. P. Ramaciotti Morales and J.-P. Cointet, "Auditing the effect of social network recommendations on polarization in geometrical ideological spaces," in Proceedings of the 15th ACM Conference on Recommender Systems, 2021, pp. 627-632.
  18. F. Huszár, S. I. Ktena, C. O'Brien, L. Belli, A. Schlaikjer, and M. Hardt, "Algorithmic amplification of politics on twitter," Proceedings of the National Academy of Sciences, vol. 119, no. 1, p. e2025334119, 2022.
  19. T. Lazovich, L. Belli, A. Gonzales, A. Bower, U. Tantipongpipat, K. Lum, F. Huszar, and R. Chowdhury, "Measuring disparate outcomes of content recommendation algorithms with distributional inequality metrics," Patterns, vol. 3, no. 8, p. 100568, 2022.
  20. A. El-Kishky, T. Markovich, S. Park, C. Verma, B. Kim, R. Eskander, Y. Malkov, F. Portman, S. Samaniego, Y. Xiao et al., "Twhin: Embedding the twitter heterogeneous information network for personalized recom- 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) mendation," in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 2842-2850.
  21. N. Alipourfard, B. Nettasinghe, A. Abeliuk, V. Krishnamurthy, and K. Lerman, "Friendship paradox biases perceptions in directed net- works," Nature communications, vol. 11, no. 1, p. 707, 2020. 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

Cited by

Sorted by citations

Authors
Bartley, N., Burghardt, K., & Lerman, K.
Affiliations
University of Southern California (US)
ORCID
Venue
Proceedings of the International Conference on Advances in Social Networks Analysis and Mining
Publisher
ACM
Published
2023-11-06
Pages
379-383
DOI
10.1145/3625007.3627724
OpenAlex
W4392845536
Cited by
4
References
2
Citations by year
2025: 2 · 2024: 2
FWCI
1.03
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
Keywords
personalized news feeds, social networking sites, chronological ordering, recommendation algorithms, agent-based modeling, network influence, algorithmic bias

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