Polarization in Decentralized Online Social Networks
Open accessAbstract
Centralized social media platforms are currently experiencing a shift in user engagement, drawing attention to alternative paradigms like Decentralized Online Social Networks (DOSNs). The rising popularity of DOSNs finds its root in the accessibility of open-source software, enabling anyone to create a new instance (i.e., server) and participate in a decentralized network known as Fediverse. Despite this growing momentum, there has been a lack of studies addressing the effect of positive and negative interactions among instances within DOSNs. This work aims to fill this gap by presenting a preliminary examination of instances’ polarization in DOSNs, focusing on Mastodon — the most widely recognized decentralized social media platform, boasting over 10M users and nearly 20K instances to date. Our results suggest that polarization in the Fediverse emerges in unique ways, influenced by the desire to foster a federated environment between instances, also facilitating the isolation of instances that may pose potential risks to the Fediverse.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
The global landscape of AI ethics guidelines
Jobin, A., Ienca, M., & Vayena, E. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0088-2 · Cited by 6,220 · see citing works
Bansal, N., Blum, A. L., & Chawla, S. (2004) · Machine Learning · doi:10.1023/b:mach.0000033116.57574.95 · Cited by 1,097 · see citing works
Extracting the multiscale backbone of complex weighted networks
Serrano, M. Á., Boguñá, M., & Vespignani, A. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0808904106 · Cited by 898 · cited 1× · see citing works
“Therefore, we resorted to the theoretically well-rooted Disparity Filter [28] method, which exploits a generative null model built on node strengths to prune networks from statistically irrelevant edges based on 𝑝 -value computation and speci fi c signi fi cance thresholds.”
MethodSpectral Analysis of Signed Graphs for Clustering, Prediction and Visualization
Kunegis, J., Schmidt, S., Lommatzsch, A., et al. (2010) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972801.49 · Cited by 379 · see citing works
Community Interaction and Conflict on the Web
Kumar, S., Hamilton, W. L., Leskovec, J., & Jurafsky, D. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186141 · Cited by 333 · cited 1× · see citing works
“In the past few years, we have witnessed a plethora of studies about user polarization on social media [5, 6, 9, 10, 14, 17].”
BackgroundDecentralized Online Social Networks
Datta, A., Buchegger, S., Vu, L., Strufe, T., & Rzaḑca, K. (2010) · Springer eBooks · doi:10.1007/978-1-4419-7142-5_17 · Cited by 168 · see citing works
Reducing Controversy by Connecting Opposing Views
Garimella, K., De Francisci Morales, G., Gionis, A., & Mathioudakis, M. (2017) · Proceedings of the Tenth ACM International Conference on Web Search and Data Mining · doi:10.1145/3018661.3018703 · Cited by 165 · cited 1× · see citing works
“In the past few years, we have witnessed a plethora of studies about user polarization on social media [5, 6, 9, 10, 14, 17].”
BackgroundChallenges in the Decentralised Web: The Mastodon Case
Raman, A., Joglekar, S., Cristofaro, E. D., Sastry, N., & Tyson, G. (2019) · Proceedings of the Internet Measurement Conference · doi:10.1145/3355369.3355572 · Cited by 118 · cited 1× · see citing works
“Among the plethora of decentralized services developed in recent years, Mastodon stems as the most widely recognized and studied [3, 23, 24, 26, 27] decentralized social media, boasting a user base exceeding 10M and nearly 20K instances to date, thus serving as the best representative for delving…”
BackgroundScalable clustering of signed networks using balance normalized cut
Chiang, K.-Y., Whang, J. J., & Dhillon, I. S. (2012) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2396761.2396841 · Cited by 83 · see citing works
Managing social contents in Decentralized Online Social Networks: A survey
Guidi, B., Conti, M., Passarella, A., & Ricci, L. (2018) · Online Social Networks and Media · doi:10.1016/j.osnem.2018.07.001 · Cited by 82 · see citing works
Understanding the growth of the Fediverse through the lens of Mastodon
Cava, L. L., Greco, S., & Tagarelli, A. (2021) · Applied Network Science · doi:10.1007/s41109-021-00392-5 · Cited by 80 · cited 2× · see citing works
“As part of this process, already having been proven meaningful in [20], we systematically expanded the user exploration by incrementally discovering new users through the link detection mechanism.”
BackgroundSelf-citationDiscovering Polarized Communities in Signed Networks
Bonchi, F., Galimberti, E., Gionis, A., et al. (2019) · Institutional Research Information System University of Turin (University of Turin) · doi:10.1145/3357384.3357977 · Cited by 76 · see citing works
Quantifying ideological polarization on a network using generalized Euclidean distance
Hohmann, M., Devriendt, K., & Coscia, M. (2023) · Science Advances · doi:10.1126/sciadv.abq2044 · Cited by 74 · see citing works
Flocking to Mastodon: Tracking the Great Twitter Migration
He, J., Zia, H. B., Castro, I., Raman, A., Sastry, N., & Gareth Tyson, A. (2023) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3618257.3624819 · Cited by 51 · see citing works
Drivers of social influence in the Twitter migration to Mastodon
Cava, L. L., Aiello, L. M., & Tagarelli, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-48200-7 · Cited by 48 · see citing works
Self-citationCava, L. L., Greco, S., & Tagarelli, A. (2022) · Online Social Networks and Media · doi:10.1016/j.osnem.2022.100220 · Cited by 46 · cited 1× · see citing works
“The impact of decentralization of user relations has been also investigated, unveiling the emergence of strategic user roles [21] and characterizing the information consumption-production dichotomy in such a novel social context [22].”
BackgroundSelf-citationNetwork Analysis of the Information Consumption-Production Dichotomy in Mastodon User Behaviors
Cava, L. L., Greco, S., & Tagarelli, A. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19391 · Cited by 26 · see citing works
Self-citationCoscia, M., & Rossi, L. (2022) · PLoS ONE · doi:10.1371/journal.pone.0263184 · Cited by 24 · see citing works
An Exploration of Decentralized Moderation on Mastodon
Bono, C. A., La Cava, L., Luceri, L., & Pierri, F. (2024) · ACM Web Science Conference · doi:10.1145/3614419.3644016 · Cited by 18 · see citing works
Self-citationWhen Correlation Clustering Meets Fairness Constraints
Gullo, F., Cava, L. L., Mandaglio, D., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18840-4_22 · Cited by 3 · see citing works
Self-citation14. Decentralized Online Social Networks
Diewald, N. (2012) · De Gruyter eBooks · doi:10.1515/9783110224948.461 · Cited by 2 · see citing works
User Migration across Multiple Social Media PlatformsPreprint
Jeong, U., Nirmal, A., Jha, K., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.12613 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- Michael Conover, Jacob Ratkiewicz, Matthew Francisco, Bruno Gonçalves, Filippo Menczer, and Alessandro Flammini. 2011. Political polarization on Twitter. In Proc. ICWSM Conf.89–96.
- Mihai Cucuringu, Peter Davies, Aldo Glielmo, and Hemant Tyagi. 2019. SPONGE: A generalized eigenproblem for clustering signed networks. In Proc. AISTATS Conf.1088–1098.
- Ruo-Chun Tzeng, Bruno Ordozgoiti, and Aristides Gionis. 2020. Discovering conflicting groups in signed networks. Proc. NIPS Conf. 33 (2020), 10974–10985.
- Matteo Zignani, Sabrina Gaito, and Gian Paolo Rossi. 2018. Follow the “Mastodon”: Structure and Evolution of a Decentralized Online Social Network. In Proc. ICWSM Conf.AAAI Press, 541–551.
- Matteo Zignani, Christian Quadri, Sabrina Gaito, Hocine Cherifi, and Gian Paolo Rossi. 2019. The Footprints of a “Mastodon”: How a Decentralized Architecture Influences Online Social Relationships. In Proc. InfoCom Workshops. 472–477.
Cited by
Sorted by citations
An Exploration of Decentralized Moderation on Mastodon
Bono, C. A., La Cava, L., Luceri, L., & Pierri, F. (2024) · ACM Web Science Conference · doi:10.1145/3614419.3644016 · Cited by 18 · see citing works
Self-citationShi, L., & Li, M. (2025) · Global Media and China · doi:10.1177/20594364251348583 · Cited by 11 · see citing works
“This decentralized nature of technological discourse on social media further enriches sociotechnical imaginaries, facilitating diverse and cross-cultural perspectives on emerging technologies (La Cava, Mandaglio, & Tagarelli, 2024).”
Defining, Detecting, and Characterizing Power Users in Threads
Bonifazi, G., Buratti, C., Corradini, E., et al. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9030069 · Cited by 4 · see citing works
“For example, several papers have analyzed Twitter (now X) [8,9,32–34], BlueSky [10,35,36], and Mastodon [11–13].”
A Herd of Young Mastodonts: the User-Centered Footprints of Newcomers After Twitter Acquisition
Cursi, F. D., Boldrini, C., Passarella, A., et al. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825038 · Cited by 2 · see citing works
“In another study [18], they explored polarization using a signed network, identifying positive (following) and negative (instance ban) relationships.”
Decentralized Discourse: Interaction Dynamics on Mastodon
Brauweiler, M., Chaitanya, M., Pfeffer, J., & Brandes, U. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717887 · Cited by 2 · see citing works
Characterizing NFT markets through a multilayer network approach
Galdeman, A., Cava, L. L., Zignani, M., Tagarelli, A., & Gaito, S. (2025) · Blockchain Research and Applications · doi:10.1016/j.bcra.2025.100356 · Cited by 2 · see citing works
Self-citationInvestigating Echo-Chambers in Decentralized Social Networks: A Mastodon Case Study
Huitema, I. R., Oskooei, A. R., Aktaş, M. S., & Riveni, M. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-82431-9_26 · Cited by 3 · see citing works
Mandaglio, D., & Tagarelli, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00171-8 · Cited by 1 · see citing works
Self-citationMoreno, F., Perdomo-Quinteiro, P., Hernández-Peñaloza, G., Álvarez, F., Belmonte-Hernández, A., & Barbero-Álvarez, M. A. (2026) · Social Network Analysis and Mining · doi:10.1007/s13278-025-01567-z
“In addition, the Fediverse tends to be less polarized, with 97% of instances classified as neutral according to La Cava et al. (2024 ).”
Top-k Diverse Polarized Communities in Signed Networks
Gullo, F., Mandaglio, D., & Tagarelli, A. (2026) · Machine Learning · doi:10.1007/s10994-026-07098-8
“Detecting polarized communities in such networks is crucial for understanding group dynamics in political debates, online discussions, and social conflicts (Nettasinghe et al., 2025 ; La Cava et al., 2024), as well as for designing interventions to mitigate harmful divisions.”
Self-citationPolarized Communities in Mastodon: Insights from Instance-Level Analysis (Discussion Paper)
Cava, L. L., Mandaglio, D., & Tagarelli, A. (2025) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat67162.2025.00103
“In this paper, we discuss our recent work [10] that properly addresses the aforementioned gap in the literature by conducting the first investigation of the polarization phenomena at the instance level within Mastodon.”
InfluentialSelf-citation
- Authors
- La Cava, L., Mandaglio, D., & Tagarelli, A.
- Affiliations
- DIMES, University of Calabria, Italy
- University of Calabria (IT)
- Venue
- ACM Web Science Conference
- Publisher
- ACM
- Published
- 2024-05-21
- Pages
- 48-52
- OpenAlex
- W4394902777
- Cited by
- 11
- References
- 12
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 3
- FWCI
- 27.60
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Web Science Conference (WebSci) (publishedVersion, cc-by)
- Archive of Doctoral Theses and Digital Collections (University of Calabria) (submittedVersion)
- Topics
- Social Sciences › Communication › Social Media and Politics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- decentralized online social networks, Fediverse, Mastodon, polarization, social networking sites, federated networks, user engagement, open source software
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
