Users Polarization on Facebook and Youtube
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Users online tend to select information that support and adhere their beliefs, and to form polarized groups sharing the same view-e.g. echo chambers. Algorithms for content promotion may favour this phenomenon, by accounting for users preferences and thus limiting the exposure to unsolicited contents. To shade light on this question, we perform a comparative study on how same contents (videos) are consumed on different online social media-i.e. Facebook and YouTube-over a sample of 12M of users. Our findings show that content drives the emergence of echo chambers on both platforms. Moreover, we show that the users' commenting patterns are accurate predictors for the formation of echo-chambers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This phenomenon is particularly pronounced in segregated networks, such as”
From A systematic review of echo chamber research: comparative analysis of conceptualizations, operationalizations, and varying outcomes (2025) · cites this paper as [47]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Real and present concerns exist over the role of mis- and disinformation in public discourse (116–118), the emergence of echo chambers (119) and deepening political polarization (120, 121), in particular around big societal issues like climate change (122).”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [120]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Dalapicolla, J., do Prado, J. R., Percequillo, A. R., & Knowles, L. L. (2021) · Journal of Biogeography · doi:10.1111/jbi.14281 · Cited by 11,461
Between Facts and Norms: Contributions to a Discourse Theory of Law and Democracy
Habermas, J. (1996) · The MIT Press eBooks · doi:10.7551/mitpress/1564.001.0001 · Cited by 9,998
Power-Law Distributions in Empirical Data
Clauset, A., Shalizi, C. R., & Newman, M. E. J. (2009) · SIAM Review · doi:10.1137/070710111 · Cited by 8,019 · cited 1×
“Scaling exponents of power law distributions are estimated via maximum likelihood (ML) as shown in [28].”
MethodPower-law distributions in empirical data
Clauset, A. J., Shalizi, C. R., & Newman, M. E. J. (2018) · Figshare · doi:10.1184/r1/6586835.v1 · Cited by 6,504
Dewey, J. (1927) · University of Michigan Library Repository · Cited by 4,147
Greene, W. (2000) · University of Maribor digital library (University of Maribor) · Cited by 3,746
Between facts and norms: contributions to a discourse theory of law and democracy
(1997) · Choice Reviews Online · doi:10.5860/choice.34-2995 · Cited by 3,574 · cited 1×
“The emergence of polarization in online environments might reduce viewpoint heterogeneity, which has long been viewed as an important component of strong democratic societies [7,8].”
BackgroundWhen Corrections Fail: The Persistence of Political Misperceptions
Nyhan, B., & Reifler, J. (2010) · Political Behavior · doi:10.1007/s11109-010-9112-2 · Cited by 3,173
An introduction to MCMC for machine learning.
Andrieu, C., de Freitas, N., Doucet, A., & Jordan, M. I. (2003) · Machine Learning · doi:10.1023/a:1020281327116 · Cited by 2,451
Cited by
Items 201–286 of 286
Lived Experiences of the COVID-19 Pandemic Among the Vietnamese Population in the Region of Peel
Cao, T., Rishworth, A., Wilson, K., Ali, F., & Gallaway, T. (2023) · Journal of Racial and Ethnic Health Disparities · doi:10.1007/s40615-023-01804-1 · Cited by 2
“…content and algorithms on social media sites such as Facebook and YouTube have been associated with creating echo chambers where users are only exposed to content similar to their beliefs, creating a cycle where users only interact with perspectives and opinions they deem accurate [35, 36].”
Problems of fake news analysis in social media
Aigelova, A., & Ishanova, A. K. (2023) · Bulletin of L N Gumilyov Eurasian National University JOURNALISM Series · doi:10.32523/2616-7174-2023-142-1-97-103 · Cited by 3
Alsinet, T., Argelich, J., Béjar, R., & Martínez, S. (2024) · Algorithms · doi:10.3390/a17080369 · Cited by 1
Park, C. S., & Molla, M. A. M. (2025) · Howard Journal of Communications · doi:10.1080/10646175.2025.2587082 · Cited by 2
“For example, this platform may foster ideological polarization and incivility (Bessi et al., 2016).”
Chua, A. Y. K., & Han, J. (2026) · Information Research · doi:10.47989/ir31iconf64270 · Cited by 1
“Since the evaluations of the same product may sometimes vary between video content creators and their users, conflicting views arise (Bessi et al., 2016).”
Wang, X., Liu, Y., Wu, S., Zhao, Z., Hu, Y., Li, W., & Bai, Q. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134333 · Cited by 4
Buturoiu, R., Corbu, N., & Boţan, M. (2023) · Springer studies in media and political communication · doi:10.1007/978-3-031-41954-6_6 · Cited by 1
Ribeiro, T. M. R., Siqueira, S. W. M., & de Bayser, M. G. (2024) · Simpósio Brasileiro de Sistemas Colaborativos (SBSC) · doi:10.5753/sbsc.2024.238053 · Cited by 1
Online Public Debate. How Can We Make It More Intelligent?
Olszowski, R. (2024) · Contributions to political science · doi:10.1007/978-3-031-58191-5_4 · Cited by 4
Lapchit, S., Suktam, W., Supsin, J., & Kenaphoom, S. (2024) · Practice, progress, and proficiency in sustainability · doi:10.4018/979-8-3693-7989-9.ch009 · Cited by 1
Investigating Microcelebrity Practices on YouTube in Pakistan: A Qualitative Analysis
Ayub, A., & Ali, M. F. (2023) · Online Media and Society · doi:10.71016/oms/ygv09681 · Cited by 1
“This shift has enabled ordinary citizens to attain fame and success and achieve celebrity status through microcelebrity practices (Bessi et al., 2016).”
Ramírez‐Cifuentes, D., Baeza-Yates, R. A., Lozano, M., & Freire, A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0312766 · Cited by 2
“…recommender systems, which are designed to suggest social connections or contacts to users within a digital platform, aiming to enhance networking and social interaction by identifying potentially valuable connections based on shared interests, mutual connections, or behavioral patterns [11].”
Computational propaganda campaigns by domestic political actors in Pakistan on Facebook
Mustafa, H., Luczak–Roesch, M., & Johnstone, D. (2026) · Journal of Computational Social Science · doi:10.1007/s42001-026-00502-2 · Cited by 1
“This sophisticated mixing makes such campaigns particularly effective, as they can resonate with distinct audi - ences by leveraging a diverse range of emotions and types of information [38–41].”
Kaur, H., Pannu, H. S., & Malhi, A. K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07903-8 · Cited by 1
Ganie, A. G., & Dadvandipour, S. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-82322-1_1 · Cited by 2
Han, Y. (2021) · NC Digital Online Collection of Knowledge and Scholarship (The University of North Carolina at Greensboro) · Cited by 1
van den Hoogen, A., Drielsma, I. H., Eshuis-Peters, E., & Wielenga, J. M. (2022) · Springer eBooks · doi:10.1007/978-3-030-91339-7_7 · Cited by 1
Fake news and the Dutch YouTube political debate space
Tuters, M. (2020) · Amsterdam University Press eBooks · doi:10.2307/j.ctv1b0fvs5.9 · Cited by 1
The framings of the coexistence of agrifood models: a computational analysis of French media
Ollivier, G., Gasselin, P., & Batifol, V. (2024) · Agriculture and Human Values · doi:10.1007/s10460-023-10531-6 · Cited by 1
“Indeed, the debates on social media encourage one-upmanship, polarization, and thinly argued shortcuts that actually degrade the quality of public debate (Bessi et al. 2016; Bail et al. 2018).”
Hong, S. J. (2024) · Springer eBooks · doi:10.1007/978-3-031-49084-2_6 · Cited by 2
Good and Bad Science? Spanish-Speaking YouTube Users’ Comments on Science Content
Serrano-Contreras, I.-J., Marin, J. G., & Luengo, Ó. G. (2024) · International Journal of Public Opinion Research · doi:10.1093/ijpor/edae045 · Cited by 1
Exposure to Opposing Views on Social Media: A Critical Analysis of Studies, Theory, and the Medium
Chaudhary, S., & Schatzki, T. R. (2025) · Journal of Social Philosophy · doi:10.1111/josp.70019 · Cited by 1
Towards the Modeling of Behavioral Trajectories of Users in Online Social MediaPreprint
Bessi, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05778 · Cited by 3
“Over the last decade, the rise of online social media has caused a huge shift in the way people find information, interpret facts, and shape their opinions.”
BackgroundSelf-citationDISCUTINDO O GÊNERO WEBCOMIC: O PAPEL DA AVALIATIVIDADE NO MULTILETRAMENTO CRÍTICO EM LÍNGUA INGLESA
dos Santos, R. C. (2018) · Pesquisas em discurso pedagógico · doi:10.17771/pucrio.pdpe.34127
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0007
A growing network for cultural transmission
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0001
Polarization Model of Online Social Networks Based on the Concept of Spontaneous Symmetry BreakingPreprint
Aida, M., Hashizume, A., Takano, C., & Murata, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.05393
“Social polarization and the echo-chamber effect have been investigated using real data of information networks; [1] analyzed Web browsing log data gathered from SNS and search engines, [2] analyzed Facebook data, while [3] examined both Facebook and YouTube data.”
MethodModelling the Influence of Social Media on Collective Opinion
Ohnishi, T. (2020) · American Journal of Physics and Applications · doi:10.11648/j.ajpa.20200806.11
“Notwithstanding, our method is a useful approach to estimate the extent of influence of the social media on the public so that we expect to improve our model by accumulating more realistic data [43, 44] and analyzing by using those data [26], especially the data of the time scale for the public to forget the informati…”
BackgroundMethodDi lessico e altre quisquilie: autopercezione ed eteropercezione linguistica nel social networking
Gheno, V. (2021) · Strumenti per la didattica e la ricerca · doi:10.36253/978-88-5518-403-8.10
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0005
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0004
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0002
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0003
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0006
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0008 · Cited by 1
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.003.0009
Data mining of IoT based sentiments to classify political opinions
Manzoor, A., Rehman, Z. U., Shaheen, M., & Khan, M. Z. (2022) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2022.2093406 · Cited by 1
“The authors extend their analysis by examining the polarisation dynamics as to how users become more polarised based on their comments (Bessi et al., 2016).”
BackgroundReposting Service in Online Social Networks: Modeling and Online Incentive Protocols
Zheng, S., Liu, X., Xie, H. L., & Lui, J. C. S. (2022) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp55882.2022.9940336
“Firstly, some works study visibility from a measurement perspective [15], [16], which revealed insights into the pattern of visibility of different users.”
BackgroundFrom Class War to Race War: Historicizing the Devolution from New Deal Populism to “Trumpism”.
King, A. (2022) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2022-15306
Omar, R. G. A. S. (2022) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · doi:10.6035/14111.2022.804915
Holanda, L. N., & Teixeira, F. C. (2023) · Revista Foco · doi:10.54751/revistafoco.v16n2-127
Silva, E. C. D. M., & de Oliveira, A. G. N. (2023) · International Conference on Theory and Practice of Electronic Governance · doi:10.1145/3614321.3614373 · Cited by 1
“Furthermore, Bessi et al. [23] argues that information tends to create such “echo chambers”, where, for example, a publication with comments supporting such content, can lead people to attribute greater credibility, which reinforces cycles of disinformation.”
BackgroundOlszowski, R. (2023) · The Eurasia Proceedings of Educational and Social Sciences · doi:10.55549/epess.1413293
Quantifying Opinion Rejection: A Method to Detect Social Media Echo Chambers
Perera, K., & Karunasekera, S. A. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2266-2_5 · Cited by 4
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.002.0006
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.002.0005
Acerbi, A. (2019) · Oxford University Press eBooks · doi:10.1093/oso/9780198835943.002.0003
Climate Change Skeptics and the Power of Negativity
Liu, Q., Kim, Y., & Hemsley, J. (2024) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1166
“Evidence show YouTube’s recommender algorithm heightens individual political opinions’ polarization (Cho et al., 2020) and YouTube users prioritize conspiracy theories over scientific mainstream views (Allgaier, 2019; Bessi et al., 2016), all which may lead to polarized commenting patterns.”
Social Media Networks, Social Support, and Misinformation During Crisis Situations
Wright, K. B. (2024) · Wiley eBooks · doi:10.1002/9781394184972.ch2 · Cited by 1
Demirhan, E. (2022) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc1944369
Schmalenbach, K., Gengler, E. J., Schötteler, S., & Laumer, S. (2025) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-80119-8_5
Ren, C. S. (2025) · Lecture Notes in Education Psychology and Public Media · doi:10.54254/2753-7048/2025.23015
Shi, X., Chen, Z., & Liu, Y. (2025) · Communications in Humanities Research · doi:10.54254/2753-7064/2024.22808
Zhang, J. (2025) · Lecture Notes in Education Psychology and Public Media · doi:10.54254/2753-7048/2025.mu22681
Facebook’s scandals and outage test users’ frenemy relationship
Stoycheff, E. (2021) · The Conversation · doi:10.64628/aai.uxr56w6w3
How Facebook went from friend to frenemy
Stoycheff, E. (2019) · The Conversation · doi:10.64628/aai.whh9rqqsp
Bagaimana Facebook berubah dari teman menjadi kawan sekaligus musuh
Stoycheff, E. (2019) · The Conversation · doi:10.64628/aan.ms5yqhdws
Do conspiracy-theory interventions rest on a mistake?
Colyvan, M., Smartt, T., & Tierney, H. (2025) · Synthese · doi:10.1007/s11229-025-05257-3 · Cited by 2
“31 As we saw, it took Facebook and other social media corporations years before they were able to effectively curb the pres - ence of QAnon content, in part because their own algorithms promote the sharing of precisely this kind of information (e.g., Alfano et al., 2021 , and Bessi et al., 2016).”
Collective incentives improve group accuracy by reducing reliance on shared news sources
Pescetelli, N., Rutherford, A., Rahwan, I., & Kao, A. B. (2025) · Collective Intelligence · doi:10.1177/26339137251372605
“…(Pennycook and Rand, 2019), emphasizing a publisher ’ s reliability (Dias et al., 2020), and predicting the spread of rumors and misinformation (P Resnick, 2015; Ciampaglia et al., 2015; Bessi et al., 2016; Del Vicario et al., 2016; Bessi et al., 2015; Oh et al., 2010; Roozenbeek et al., 2020).”
Inagaki, K., & Hara, Y. (2025) · Japanese Journal of JSCE · doi:10.2208/jscejj.24-00191
Decolonizing Caribbean Heritage
Pajard, A. (2019) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-64113-733-120251013
Murphy-Morgan, C. N., & Smith, L.-A. (2025) · Imagination Cognition and Personality · doi:10.1177/02762366251384885
“The frequent accusations that fellow commenters with opposing views were ‘ just not listening ’ is consistent with previous literature evidencing polarisation on Facebook (Bessi, et al., 2016; Del Vicario, 2016).”
Additional file 1 of Modeling algorithmic bias: simplicial complexes and evolving network topologies
Pansanella, V., Rossetti, G., & Milli, L. (2022) · Figshare · doi:10.6084/m9.figshare.20499861
Echo-Politics: Political Fragmentation, Echo Chambers and Polarization in Online Turkish Society
OZAYDIN, S. Y., & Ozaydin, S. Y. (2023) · Institutional Repositories DataBase (IRDB)
Rabina, D. J., Natuel, R. M., & Ordoñez, J. P. (2025) · The Research Probe · doi:10.53378/trp.197
“The repetition of such symbols reinforces affective polarization (Iyengar et al., 2019), and social media algorithms further amplify their divisive potential by prioritizing emotionally reactive content (Bessi et al., 2016; Gal et al., 2016).”
Brines, L. A. (2025) · Revista Electrónica de Lingüística Aplicada · doi:10.58859/rael.v24i1.664
Gan, W., Xiao, M., & Zhang, N. (2025) · Journal of Social Development and History · doi:10.71052/jsdh/ydtc2843
KETERLIBATAN ALGORITMA DI ATAS IKATAN AUTENTIK: PERAN MEDIA SOSIAL YANG TERUS BEREVOLUSI
Makarawung, R. J. N., Sutrisno, J., & Raditya, D. (2026) · JATI (Jurnal Mahasiswa Teknik Informatika) · doi:10.36040/jati.v10i1.17556
The Entanglement of Usability and Sociability: Discord in the Time of Monsters
Greentree, J. (2026) · Queensland University of Technology · doi:10.5204/thesis.eprints.263534
Chomel, V. (2022) · theses.fr (ABES) · doi:10.70675/9ee41aa0ze5d3z436ezb779zd17f5ee3e142 · Cited by 1
Continuous growth of social polarization for scale-free networks
Pan, B., & Liu, J. (2026) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0322613
Nguyen, Q. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.131965
Framing and Bias in Shared Media: Cross-Platform Analysis of Polarized Political Communities
Buzelin, A., Aquino, Y., Bento, P., Malaquias, S., Estanislau, V., Chagas, A., Dayrell, L., Pappa, G. L., Almeida, V. A. F., & Meira, W. (2026) · ACM Symposium on Applied Computing · doi:10.1145/3748522.3780016
Leo, V. D., Puliga, M., Erba, M., Scalia, C., Filetti, A., & Chessa, A. (2026) · Complexities · doi:10.3390/complexities2020015
“Combined with natural cognitive biases, this information deluge fosters polarization and a competitive struggle for attention, as noted by Bessi et al. [6] and Weng et al. [7].”
Self-citationNegativity vs. Incivility: How We Engage with Partisan Content on Facebook Over Time
Kim, Y. (2026) · Mass Communication & Society · doi:10.1080/15205436.2026.2687879
Is Algorithm the Culprit of Information Cocoons: A Systematic Literature Review
Liu, Y., Zhao, H., & Lin, Y. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2688495
Chen, X., Lin, J., & Zhong, Z. (2026) · Online Social Networks and Media · doi:10.1016/j.osnem.2026.100351
Brack, N., & Marczyński, P. (2026) · Palgrave Studies in European Political Sociology · doi:10.1007/978-3-032-13933-7_8
Identification and Categorization of Polarized Fluoride Messages in Facebook Posts.
Jucá, A. M., Leite, J. R., Jorge, O., Lotto, M., & Cruvinel, T. (2026) · JDR Clinical & Translational Research · doi:10.1177/23800844261464610
Anti-Elitism Gets the Views: Populist Communication and Popularity on German Political YouTube
Erhard, L. (2026) · The International Journal of Press/Politics · doi:10.1177/19401612261468863
Hong, F., Xia, S., & Zhang, C. (2026) · Perspectives on Politics · doi:10.1017/s1537592726105751
Bajuwaiber, N. (2026) · Telematics and Informatics Reports · doi:10.1016/j.teler.2026.100384
Cross-channel users' hostile expression on YouTube: Evidence from digital trace data
Lin, H. Y., & Kim, B. (2026) · Telematics and Informatics · doi:10.1016/j.tele.2026.102471
Metadata
- Authors
- Bessi, A., Zollo, F., Del Vicario, M., Puliga, M., Scala, A., Caldarelli, G., Uzzi, B., & Quattrociocchi, W.
- Affiliations
- Istituto Universitario di Studi Superiori di Pavia (IT)
- Northwestern University (US)
- Corresponding author
- Quattrociocchi, Walter
- ORCID
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2016-08-23
- Volume
- 11
- Issue
- 8
- Pages
- e0159641
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC4994967
- OpenAlex
- W2339074936
- Cited by
- 285
- References
- 30
- Citations by year
- 2026: 18 · 2025: 29 · 2024: 25 · 2023: 31 · 2022: 44 · 2021: 44 · 2020: 37 · 2019: 29 · 2018: 15 · 2017: 9 · 2016: 4
- FWCI
- 54.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- IMT Institutional Repository (IMT School for Advanced Studies Lucca) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- ARCA (Università Ca' Foscari Venezia) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Commission (317532, 610704)
- Topics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Social Sciences › Communication › Social Media and Politics
- Social Sciences › Sociology and Political Science › Media Influence and Politics
- Keywords
- echo chambers, Facebook, YouTube, content consumption, commenting behavior, social media, belief reinforcement, cross-platform comparison
- MeSH terms
- Humans, Models, Theoretical, Periodicals as Topic, Internet, Information Dissemination, Social Networking, Social Media
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.