The DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index.
Big Questions for Social Media Big Data: Representativeness, Validity and Other Methodological Pitfalls
Open accessAbstract
Large-scale databases of human activity in social media have captured scientific and policy attention, producing a flood of research and discussion. This paper considers methodological and conceptual challenges for this emergent field, with special attention to the validity and representativeness of social media big data analyses. Persistent issues include the over-emphasis of a single platform, Twitter, sampling biases arising from selection by hashtags, and vague and unrepresentative sampling frames. The socio-cultural complexity of user behavior aimed at algorithmic invisibility (such as subtweeting, mock-retweeting, use of “screen captures” for text, etc.) further complicate interpretation of big data social media. Other challenges include accounting for field effects, i.e. broadly consequential events that do not diffuse only through the network under study but affect the whole society. The application of network methods from other fields to the study of human social activity may not always be appropriate. The paper concludes with a call to action on practical steps to improve our analytic capacity in this promising, rapidly-growing field.
Overview
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.
Integrity signals
Registry
Cites
Statistics
Verification
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.
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
“Social data opens unprecedented opportunities to answer significant questions about society, policies, and health, being recognized as one core reason behind progress in many areas of computing (e.g., crisis informatics, digital health, computational social science) (Crawford and Finn, 2014; Tufekci, 2014; Yom-Tov, 2016).”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The behaviors we observe in online social platforms are partially determined by platform capabilities, which are engineered toward certain goals”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The functional peculiarities of social platforms may introduce population (section 3.2) and behavioral biases (section 3.3) by influencing which user demographics are drawn to each platform and the kind of actions they are more likely to perform”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Overlooking the impact of norms can impact any social data analysis studying or making assumptions about user behavior”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“if the data is organized along a certain attribute (e.g., the presence of a keyword or hashtag), and there are multiple independent factors that result in the attribute taking a certain value, analyzing data entries with this value is equivalent to conditioning on it, and may result in spurious patterns of association among these factors (Blyth, 1972; Tufekci, 2014).”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
Experimental — accuracy not yet measured
The cited source says what the claim attributes to it.
In the citing paper
“Yet, such implications are not always well understood or recognized (Tufekci, 2014; O'Neil, 2016), as many seem to assume that these data, and the frameworks used to handle them, are adequate, often as-is, for the problem at hand, with little or no scrutiny.”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“Regardless of how large or varied social data are, there are also lingering questions about what can be learned from them about real-world phenomena (online or offline)—which have yet to be rigorously addressed (boyd and Crawford, 2012; Ruths and Pfeffer, 2014; Tufekci, 2014).”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“A key concern is that research agendas tend to be opportunistically driven by access to data, tools, or ease of analysis (Ruths and Pfeffer, 2014; Tufekci, 2014; Weller and Gorman, 2015); or, as Baeza-Yates (2013) puts it, “we see a lot of data mining for the sake of it.””
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“much research is concentrated on data from a few platforms, most notably Twitter.”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“Functional biases make conclusions from research studies difficult to generalize or transfer, as each platform exhibits its own structural differences (Tufekci, 2014), which can lead to platform-specific phenomena (Ruths and Pfeffer, 2014) that are often overlooked.”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“For instance, we often know what people write, but not what they read, and we may know who clicked on or “liked” something, but not who read it or watched it”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“The choice of keywords in keyword-based queries shapes the resulting datasets.”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“different hashtags used in the same context (e.g., during a political event) may be associated with distinct social, political or cultural frames, and, thus, samples built using them may embed different dimensions of the data (Tufekci, 2014)”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“Many datasets are built around dependent variables (see section 5.2), deciding to include a user or a piece of content depending on the inclusion of a variable under analysis (Tufekci, 2014); this may result in apparent patterns of association that fail to generalize.”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
The cited source says what the claim attributes to it.
In the citing paper
“The same mechanism or process may capture different signals across contexts (Tufekci, 2014), but such distinctions are often unintelligible and hard to make in an automated fashion when looking at a system output or at an analysis results in aggregate (Rost et al., 2013; Tufekci, 2014).”
From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Tufekci, 2014
In the citing paper
“For instance, if a study investigates the effectiveness of a particular treatment based on data collected from a specific time period, the findings may not reflect the current healthcare landscape or advancements in medical practices [91].”
From Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond (2024) · cites this paper as [91]
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
What is Twitter, a social network or a news media?
Kwak, H., Lee, C., Park, H., & Moon, S. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772751 · Cited by 6,652
boyd, D., & Crawford, K. (2012) · Information, Communication & Society · doi:10.1080/1369118x.2012.678878 · Cited by 5,479
Lazer, D., Pentland, A., Adamic, L., Aral, S., Barabási, A.-L., Brewer, D., Christakis, N., Contractor, N., Fowler, J., Gutmann, M., et al. (2009) · Science · doi:10.1126/science.1167742 · Cited by 3,365
Measuring user influence in twitter: The million follower fallacy
Cha, M., Haddadi, H., Benevenuto, F., & Gummadi, K. (2010) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v4i1.14033 · Cited by 3,022 · cited 1×
“Another important social media study, based on Twitter, speaks of in-degree (number of followers) as a user’s popularity, and retweets as influence (Cha et al., 2010).”
BackgroundSocial Media and the Decision to Participate in Political Protest: Observations From Tahrir Square
Tüfekçi, Z., & Wilson, C. (2012) · Journal of Communication · doi:10.1111/j.1460-2466.2012.01629.x · Cited by 1,660
Whose space? differences among users and non-users of social network sites
Hargittai, E. (2007) · Journal of Computer-Mediated Communication · doi:10.1111/j.1083-6101.2007.00396.x · Cited by 1,286
Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures
Golder, S. A., & Macy, M. W. (2011) · Science · doi:10.1126/science.1202775 · Cited by 1,155 · cited 1×
“…and allow us to observe social phenomena at a previously unthinkable level, such as the mood oscillations of millions of people in 84 countries (Golder et al., 2011), or in cases where there is arguably no other feasible method Copyright © 2014, Association for the Advancement of Artificial…”
MethodRomero, D. M., Meeder, B., & Kleinberg, J. (2011) · Proceedings of the 20th international conference on World wide web · doi:10.1145/1963405.1963503 · Cited by 1,082
Information contagion: an empirical study of the spread of news on digg and twitter social networks
Lerman, K., & Ghosh, R. (2010) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v4i1.14021 · Cited by 813
Research works printed but not linked: 3
- [4]4. Allison, P.D. 2001. Missing data. Thousand Oaks, CA: SAGE.
- [8]8. boyd, d., and Crawford, K. 2012. Critical Questions for Big Data. Information, Communication & Society 15 (5): 662-679.
- [28]28. Pray, L. & Zhaurova, K. (2008) Barbara McClintock and the discovery of jumping genes (transposons). Nature Education 1(1):169
Cited by
Sorted by citations
Items 701–771 of 771
عادل, ن. (2023) · المجلة العلمية لبحوث الصحافة · doi:10.21608/sjsj.2023.337684
Observer Effect in Social Media UsePreprint
Saha, K., Gupta, P., Mark, G. J., Kıcıman, E., & Choudhury, M. D. (2024) · Research Square · doi:10.21203/rs.3.rs-2492994/v3
Mohammed, A. A., & Hamed, P. K. (2024) · International Journal of Academic Research in Progressive Education and Development · doi:10.6007/ijarped/v13-i1/20889
Supplementing Sensitive Survey Data by Leveraging Social Listening with Machine Learning Models
Smalley, H. K., & Orr, J. W. (2023) · doi:10.1109/bigsurv59479.2023.10486518
Busch, C., Specht, K., Inostroza, L., Falke, M., & Zepp, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4827804
Jones, M. A. (2024) · doi:10.1093/oso/9780198899457.003.0006
Moreno-Martínez, Ó. (2023) · Signo y Pensamiento · doi:10.11144/javeriana.syp42.cvev
Harnessing AI for Political Engagement
Suktam, W., Supsin, J., Lapchit, S., & Kenaphoom, S. (2024) · Practice, progress, and proficiency in sustainability · doi:10.4018/979-8-3693-7989-9.ch008
Hutchinson, J. P., Suwana, F., & McTernan, C. (2024) · Springer eBooks · doi:10.1007/978-3-031-66360-4_7
User features and gendered patterns in repeat online advice-seeking behavior
Kang, B. N. Y., Ho, M. R., & Jaidka, K. (2025) · Journal of Quantitative Description Digital Media · doi:10.51685/jqd.2025.008
A primer on data-driven modeling \@ifstar{}of complex social systems
Volkening, A. (2025) · Proceedings of symposia in applied mathematics · doi:10.1090/psapm/080/00726 · Cited by 1
Revolutionizing Research: The Transformative Role of ChatGPT in Scientific Research
Mariappan, J., Sahdev, S. L., Krishnan, C., & Malik, F. A. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83549-852-120251005
Guarding Your Digital Footprint: The Battle for Digital Privacy
Devakumar, D. T. (2025) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem49606
Digital coproduction in Seoul: the case of Seoul’s government and citizen-led platforms
Hwang, H., & Kim, R. (2025) · Local Government Studies · doi:10.1080/03003930.2025.2538230
Operationalising AIS Bias ManagementPreprint
Albalkhi, R., Leppälä, J., & Padget, J. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5383231
Marcos de injusticia en el contexto del 8 de marzo
Sosa, A. Z., & Lena, M. M.-L. (2021) · Enseñanza e investigación en psicología · doi:10.62364/gg6z5y70
Migration, Pflegearbeit und Social Media
Rahnoma, H., Schlender, L., & Wichterich, C. (2025) · PROKLA Zeitschrift für kritische Sozialwissenschaft · doi:10.32387/prokla.v55i220.2194
Oğuzcan, D., & Oğuzcan, A. U. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6970-9.ch003
Sign consistency of the generalized elastic net estimator
Zhu, W., Adjakossa, E., Lévy‐Leduc, C., & Ternès, N. (2025) · Communication in Statistics- Theory and Methods · doi:10.1080/03610926.2025.2559097
FUNCTIONAL APPLICATIONS OF BIG DATA AND DIGITAL TRANSFORMATION IN SOCIAL SCIENCES
Aksu, C. (2025) · Meriç Uluslararası Sosyal ve Stratejik Araştırmalar Dergisi · doi:10.54707/meric.1571990
Using hidden Markov models to assess and correct for measurement error in digital trace data
Pankowska, P., Cernat, A., Keusch, F., & Bach, R. L. (2025) · Communication Methods and Measures · doi:10.1080/19312458.2025.2573265
New Technology and OB/HRM in China: Digital Methods for Organizational Research
Li, N., He, W., Yam, K. C., & Zhao, H. H. (2025) · Management and Organization Review · doi:10.1017/mor.2025.10103
The Social Construction of Off-label Drug Use: A Case Study of Ozempic Discourse on Social Media
Kartal, N., & Günaltay, M. M. (2025) · International Journal of Mental Health and Addiction · doi:10.1007/s11469-025-01599-8
Dijital Bilginin Epistemolojisi: Hesaplamalı Sosyal Bilimlerin Bilgi Üretimi Üzerine Etkisi
Özcan, E., & Yılmaz, B. (2025) · Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi · doi:10.17494/ogusbd.1750913
Discussion: The Evolving Science of Patient Involvement
Tjader, N. P., Crossnohere, N. L., & Bridges, J. F. P. (2026) · Health informatics · doi:10.1007/978-3-032-11284-2_8
Lee, H., Seo, S., Park, S., Tam, L., Kim, S., & Jang, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6140247
Lee, H., Seo, S., Park, S., Tam, L., Kim, S., & Jang, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6140251
Phenomenologically human: Fine-tuning LLMs to simulate online group identity
Torres, A. M., & Morselli, D. (2026) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2026.100272
Storytelling en el Reel de Instagram: impacto en la interacción digital de ONG en Quito
Ortiz, C. A. C., & Erazo-Álvarez, C. A. (2026) · Religación · doi:10.46652/rgn.v11i49.1623
Kamran, H., Dorrani, A., & Kamran, H. (2026) · Lecture notes in operations research · doi:10.1007/978-3-032-13116-4_20
Dubosson, M., & Fragnière, E. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83549-534-620251005
Patnukao, A. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-06867-z
Liu, S., Zhao, L., Liu, J., Nie, W., & Xu, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-43891-0
Europe’s Digital Political Discourse: Mapping Narratives with a Multi-Platform, Multilingual Dataset
Gayo-Avello, D., Hartland, A., García, C. G., Morales, L., Pamíes, C., Jiménez, F. R. V., Braun, D., Pérez, B. L., & Sandri, G. (2026) · The future of Europe · doi:10.1007/978-3-032-19119-9_9
Tian, J. (2026) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2026.2643717
Spécificités des sites de réseaux sociaux et effets sur le bien-être subjectif
Masciantonio, A. (2021) · theses.fr (ABES) · doi:10.70675/57037ff3z6387z4f23zba21z1eded09313d6
Understanding misinformation and fighting for information
Altay, S. (2021) · theses.fr (ABES) · doi:10.70675/2e02b9cfz3b17z4c05za865zfcbe3a9fb6e4
Nguyen, X. P., Hoang, A. T., Pham, T. D., Le, M. P., Le, T. N., & Trinh, D. B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18162-6_56
Feng, J. S., Yang, Z., Zhao, J., Anonymous, Ye, X., Lan, X., & Chen, S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791152
The Psychological Rewards of Online Self-Disclosure
Yu, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-5896-3.ch005
Discursive constructions of autism on social media: a multilingual analysis across five languages
López-Resa, P., Skafle, I., Rebecchi, K., Kalandadze, T., Nordahl‐Hansen, A., & Gabarrón, E. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1769965
Bowling leagues and facebook friends: Measuring social capital in the digital age
Leuven, A. J. V., & Malone, T. (2026) · Community Development · doi:10.1080/15575330.2026.2661178
Gaddis, S. M., Porter, N. D., & Verdery, A. M. (2017) · OSF Preprints (OSF Preprints)
Zheng, T., Huang, M., Xu, C., Liu, S., Dong, H., Ma, X., & Wang, K. (2026) · Applied Sciences · doi:10.3390/app16104803
The Driving Forces of Governments’ Positions on International Events: A Systemic Case Study
Hao, Z., Xie, M., Zhu, X., Liu, J., Xiao, H., Zhang, L., Dong, L., Liu, C., Cao, J., Dong, Z., et al. (2026) · Systems · doi:10.3390/systems14060609
Pogrebna, G., & Hills, T. T. (2026) · Cambridge University Press eBooks · doi:10.1017/9781108939010.035
Procter, R. (2026) · Cambridge University Press eBooks · doi:10.1017/9781108939010.038
Sentiment analysis of sports fans’ behaviour: A multimodal review of digital and in-venue fan affect
Ziaee, A., & Ziabari, S. S. M. (2026) · Journal of Sports Analytics · doi:10.1177/22150218261455495
Joung, E. G. (2026) · Social Science Computer Review · doi:10.1177/08944393261457540 · Cited by 2
Reconfiguring Nationalism: The Diaspora as a Catalyst Beyond Territorial Stigma
Haq, F. N., Haqqi, N. A. T., & Thaariq, Z. Z. A. (2026) · Niğde Ömer Halisdemir Üniversitesi Sosyal Bilimler Enstitüsü Dergisi · doi:10.56574/nohusosbil.1853663
An Evaluation of the Use of Digital Trace in Tax Audits and Data Privacy in Turkiye
UYGUN, E. (2026) · International Journal of Public Finance · doi:10.30927/ijpf.1816002
Campoverde, E. C. L., & Zúñiga, B. F. (2026) · Doxa Comunicación Revista interdisciplinar de estudios de comunicación y ciencias sociales · doi:10.31921/doxacom.3473
TubeStats and TokStats: Research Tools for Random Samples of YouTube and TikTok
Zheng, K., Keeney, R. G., McGrady, R., Jaisingh, V., & Zuckerman, E. (2026) · Media and Communication · doi:10.17645/mac.12085
Ciodaro, T., do Carmo, V., Ferreira, F., Lago, M., Salles, D., & Santini, R. M. (2026) · Applied Network Science · doi:10.1007/s41109-026-00810-6
Zhang, H., Feng, X., Yu, J., & Wang, M. (2026) · Buildings · doi:10.3390/buildings16142775
Chen, Z., Li, S., Zou, Y., Wu, T., Shen, C., & Wu, Z. (2026) · Sustainable Cities and Society · doi:10.1016/j.scs.2026.107831
Comment Timestamps in Interface-Level YouTube Extraction: A Measurement ReportPreprint
Sedlmair, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7416718
Sedlmair, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7416618
Li, F., & Ren, H. (2026) · Behavioral Sciences · doi:10.3390/bs16101825
Santoso, P., Kansong, U., Yulhasni, Y., & Basit, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7590250
The Contested Politics of Food: Public Moral Evaluation of Everyday Practice
(23880849), J. L., & Kınlı, İ. Ö. (2026) · The Sociological Review · doi:10.1177/00380261261490792
What the Corpus Does not say: Reply Structure, Time and Coverage in YouTube Comment DataPreprint
Sedlmair, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7606338
Meta user movement data for analysing disaster-related mobility: sensitivity, bias, and usability
Constance, G., Hubert, A., Devillet, G., & Dujardin, S. (2026) · Spatial Information Research · doi:10.1007/s41324-026-00716-6
Zhou, Y., Zhou, J., Zhao, N., & Wang, R. (2026) · Land · doi:10.3390/land15112032
Kayabaşı, E., & Çakmak, E. K. (2026) · Research Square · doi:10.21203/rs.3.rs-11217865/v1
Metadata
- Authors
- Tufekci, Z.
- Venue
- Proceedings of the International AAAI Conference on Web and Social Media
- Published
- 2014-05-16
- Volume
- 8
- Issue
- 1
- Pages
- 505-514
- ISSN
- 2162-3449 (ISSN-L)
- 2334-0770
- OpenAlex
- W2102861780
- Cited by
- 780
- References
- 27
- Citations by year
- 2026: 52 · 2025: 49 · 2024: 54 · 2023: 60 · 2022: 58 · 2021: 98 · 2020: 73 · 2019: 71 · 2018: 91 · 2017: 72 · 2016: 59 · 2015: 34 · 2014: 9
- FWCI
- 117.22
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the International AAAI Conference on Web and Social Media (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Social Sciences › Decision Sciences › Information Systems and Management › Big Data Technologies and Applications
- Social Sciences › Sociology and Political Science › Survey Methodology and Nonresponse
- Keywords
- social media big data, representativeness, validity, sampling bias, Twitter, hashtags, sampling frame, field effect, network analysis, methodological pitfalls
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
