Explanations as Mechanisms for Supporting Algorithmic Transparency
Open accessThe DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Abstract
Transparency can empower users to make informed choices about how they use an algorithmic decision-making system and judge its potential consequences. However, transparency is often conceptualized by the outcomes it is intended to bring about, not the specifics of mechanisms to achieve those outcomes. We conducted an online experiment focusing on how different ways of explaining Facebook's News Feed algorithm might affect participants' beliefs and judgments about the News Feed. We found that all explanations caused participants to become more aware of how the system works, and helped them to determine whether the system is biased and if they can control what they see. The explanations were less effective for helping participants evaluate the correctness of the system's output, and form opinions about how sensible and consistent its behavior is. We present implications for the design of transparency mechanisms in algorithmic decision-making systems based on these results.
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
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
“Rader et al. (2018) conclude that although explaining the algorithm of Facebook ' s NewsFeed increased user awareness of the algorithm, yet also caused participants to perceive the NewsFeed as less fair and more biased.”
From Explaining Why the Computer Says No: Algorithmic Transparency Affects the Perceived Trustworthiness of Automated Decision‐Making (2023) · cites this paper as Rader et al. (2018)
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“People's mental model can be refned by explanations of how the system works.”
From Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation (2022) · cites this paper as [71]
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
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Ellison, N. B., Steinfield, C., & Lampe, C. (2007) · Journal of Computer-Mediated Communication · doi:10.1111/j.1083-6101.2007.00367.x · Cited by 9,939
Understanding Information Systems Continuance: An Expectation-Confirmation Model1
Bhattacherjee, A. (2001) · MIS Quarterly · doi:10.2307/3250921 · Cited by 8,767 · cited 2×
“Finally, four questions about participants’ satisfaction with Facebook were based on Bhattacherjee [4] and Venkatesh et al. [53], and averaged to create a composite variable ( FB Satisfaction ).”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“Understanding that there are reasons why a system behaves the way it does, and evaluating whether the system is acting consistently with those reasons, makes the system’s behavior interpretable and helps users feel comfortable acting on the outputs [35].”
BackgroundHow the machine “thinks”: Understanding opacity in machine learning algorithms
Burrell, J. (2016) · Big Data & Society · doi:10.1177/2053951715622512 · Cited by 3,196 · cited 1×
“Some have argued that platforms are intentionally opaque regarding details about their operation as a form of self-protection from competitors or others who attempt to “game” the system [7].”
BackgroundAnanny, M., & Crawford, K. (2018) · New Media & Society · doi:10.1177/1461444816676645 · Cited by 1,836 · cited 9×
“Because it is difficult for explanations in algorithmic decisionmaking systems to provide clear actions for users who want to enact changes, they “place a tremendous burden on individuals” [1] to interpret the new information and figure out for themselves what it means for them and how important and relevant it is to…”
BackgroundInfluentialProceedings of the Human Factors and Ergonomics Society 2019 Annual Meeting
(2019) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181319631171 · Cited by 1,432
The Black Box Society: The Secret Algorithms That Control Money and Information
(2016) · Contemporary Sociology: A Journal of Reviews · doi:10.1177/0094306116641409c · Cited by 1,334
Gillespie, T. (2014) · Media Technologies · doi:10.7551/mitpress/9042.003.0013 · Cited by 1,016 · cited 1×
“In a social media context, algorithmic curation—automated selection and ranking of content— acts as a gatekeeper, defining what is relevant, knowable, and authoritative [27, 6, 23].”
BackgroundVenkatesh, V., Thong, J. Y. L., Chan, F. K. Y., Hu, P. J.-H., & Brown, S. A. (2011) · Information Systems Journal · doi:10.1111/j.1365-2575.2011.00373.x · Cited by 852 · cited 1×
“[53], and averaged to create a composite variable (FB Satisfaction).”
Working with Machines: The Impact of Algorithmic and Data-Driven Management on Human Workers
Lee, M. K., Kusbit, D., Metsky, E., & Dabbish, L. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702548 · Cited by 823 · cited 2×
“In others, users are motivated to become more knowledgeable about the algorithmic outputs so that they can create workarounds in an effort to avoid negative outcomes [32].”
BackgroundAccountability in algorithmic decision making
Diakopoulos, N. (2016) · Communications of the ACM · doi:10.1145/2844110 · Cited by 763 · cited 2×
“Researchers and policy-makers argue that transparency is valuable, and advocate greater transparency as a remedy for identifying and preventing various potential negative effects of these systems [12].”
BackgroundRecommender systems: from algorithms to user experience
Konstan, J. A., & Riedl, J. (2012) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9112-x · Cited by 762 · cited 2×
“Algorithms that make autonomous decisions and provide recommendations are a “mission critical” aspect of many online content and e-commerce platforms, including Facebook, Google, Netflix, and Amazon [28, 29, 39].”
BackgroundLi, X., Hess, T. J., & Valacich, J. S. (2008) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2008.01.001 · Cited by 635 · cited 1×
“[33], modified to refer to “social media” instead of “information systems”, and averaged together.”
BackgroundEslami, M., Rickman, A., Vaccaro, K., Aleyasen, A., Vuong, A., Karahalios, K., Hamilton, K., & Sandvig, C. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702556 · Cited by 627 · cited 1×
“Many Facebook users do not realize that the content in their News Feeds is curated by an algorithm [16], so they cannot react to stories in the News Feed like they would a recommendation.”
BackgroundMedia Technologies: Essays on Communication, Materiality, and Society
(2014) · The MIT Press eBooks · doi:10.7551/mitpress/9780262525374.001.0001 · Cited by 580
A Survey of Explanations in Recommender Systems
Tintarev, N., & Masthoff, J. (2007) · 2007 IEEE 23rd International Conference on Data Engineering Workshop · doi:10.1109/icdew.2007.4401070 · Cited by 566 · cited 1×
“They provide information about how a system produces a recommendation, particularly focusing on the system’s reasoning and data source [50, 51].”
BackgroundExplanations From Intelligent Systems: Theoretical Foundations and Implications for Practice1
Gregor, S., & Benbasat, I. (1999) · MIS Quarterly · doi:10.2307/249487 · Cited by 535 · cited 3×
“Explanations present information about how the system produced the recommendation and the reasons behind it [3, 24, 52], and are in service to the system’s purpose and goals [20].”
BackgroundThe Black Box Society: The Secret Algorithms That Control Money and Information
(2015) · Choice Reviews Online · doi:10.5860/choice.190706 · Cited by 533 · cited 1×
“As important responsibilities and processes are increasingly delegated to algorithmic decision-making systems [13, 56], more attention is being paid to algorithmic transparency [12, 43].”
BackgroundAlgorithmic Transparency in the News Media
Diakopoulos, N., & Koliska, M. (2017) · Digital Journalism · doi:10.1080/21670811.2016.1208053 · Cited by 515 · cited 2×
“Accountability is often discussed as the ultimate goal of transparency; it is thought to be a means of shifting the balance of power [1, 14] via increased scrutiny [13, 56].”
BackgroundRecommendation Agents for Electronic Commerce: Effects of Explanation Facilities on Trusting Beliefs
Wang, W., & Benbasat, I. (2007) · Journal of Management Information Systems · doi:10.2753/mis0742-1222230410 · Cited by 498 · cited 3×
“These explanations disclose important details about the functioning of the system to the user, and fill a knowledge gap between a user’s experiences with and intuitions about a system and the system’s actual internal processes [54].”
BackgroundThe role of transparency in recommender systems
Sinha, R., & Swearingen, K. (2002) · CHI '02 Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/506443.506619 · Cited by 477 · cited 1×
“When users believe they understand why a system makes a recommendation, they feel more comfortable and satisfied with recommendations [49], and are more willing to accept a recommendation [10].”
BackgroundThe effects of transparency on trust in and acceptance of a content-based art recommender
Cramer, H., Evers, V., Ramlal, S., van Someren, M., Rutledge, L., Stash, N., Aroyo, L., & Wielinga, B. (2008) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-008-9051-3 · Cited by 448 · cited 2×
“Explanations improve system usability and overall performance, and promote more positive user perceptions and acceptance of the system [10, 24, 21, 37].”
BackgroundZarsky, T. (2016) · Science, Technology, & Human Values · doi:10.1177/0162243915605575 · Cited by 422
Intelligent agent transparency in human–agent teaming for multi-UxV management
Mercado, J. E., Rupp, M. A., Chen, J. Y. C., Barnes, M. J., Barber, D., & Procci, K. (2016) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720815621206 · Cited by 403 · cited 3×
“Explanations improve system usability and overall performance, and promote more positive user perceptions and acceptance of the system [10, 24, 21, 37].”
BackgroundToo much, too little, or just right? Ways explanations impact end users' mental models
Kulesza, T., Stumpf, S., Burnett, M., Yang, S., Kwan, I., & Wong, W.-K. (2013) · 2013 IEEE Symposium on Visual Languages and Human Centric Computing · doi:10.1109/vlhcc.2013.6645235 · Cited by 388 · cited 2×
“Correctness judgments are a function of transparency in that a mechanism that can support an understanding of how the inputs produce the outputs [31] is necessary before an individual can evaluate for themselves “whether a system is working as intended and what changes are required” [1].”
BackgroundUnderstanding User Beliefs About Algorithmic Curation in the Facebook News Feed
Rader, E., & Gray, R. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702174 · Cited by 386 · cited 3×
“Users may become aware of an algorithm through repeated experiences with a system [46].”
BackgroundMethodInfluentialSelf-citationBreaking the filter bubble: democracy and design
Bozdag, E., & van den Hoven, J. (2015) · Ethics and Information Technology · doi:10.1007/s10676-015-9380-y · Cited by 375 · cited 2×
“In a social media context, algorithmic curation—automated selection and ranking of content— acts as a gatekeeper, defining what is relevant, knowable, and authoritative [27, 6, 23].”
BackgroundAlgorithms, Governance, and Governmentality: On Governing Academic Writing
Introna, L. D. (2016) · Science, Technology, & Human Values · doi:10.1177/0162243915587360 · Cited by 339
How should I explain? A comparison of different explanation types for recommender systems
Gedikli, F., Jannach, D., & Ge, M. (2014) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2013.12.007 · Cited by 337 · cited 3×
“Explanations improve system usability and overall performance, and promote more positive user perceptions and acceptance of the system [10, 24, 21, 37].”
BackgroundTintarev, N., & Masthoff, J. (2012) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9117-5 · Cited by 334 · cited 1×
“Explanations present information about how the system produced the recommendation and the reasons behind it [3, 24, 52], and are in service to the system’s purpose and goals [20].”
BackgroundExplaining Recommendations: Satisfaction vs. Promotion
Bilgic, M., & Mooney, R. J. (2005) · Intelligent User Interfaces · Cited by 334
Designing and Evaluating Explanations for Recommender Systems
Tintarev, N., & Masthoff, J. (2011) · Recommender Systems Handbook · doi:10.1007/978-0-387-85820-3_15 · Cited by 322 · cited 2×
“A third type of mechanism to promote greater transparency is providing explanations, a common approach in recommender systems [51] that may help solve problems caused by lack”
BackgroundDeVito, M. A., Gergle, D., & Birnholtz, J. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025659 · Cited by 311 · cited 2×
“This could represent a feeling of violated expectations, which tends to decrease satisfaction and could result in users perceiving that their goals are not being met and that the system is unfair [11, 17].”
BackgroundSuccinct survey measures of web-use skills
Hargittai, E., & Hsieh, Y. P. (2012) · Social Science Computer Review · doi:10.1177/0894439310397146 · Cited by 288 · cited 1×
“The Internet Literacy control variable is based on the Web Use Skills survey reported in Hargittai and Hsieh [25].”
MethodAttachment style, social skills, and Facebook use amongst adults
Oldmeadow, J. A., Quinn, S., & Kowert, R. (2013) · Computers in Human Behavior · doi:10.1016/j.chb.2012.10.006 · Cited by 284 · cited 1×
“We created the Routine FB Behavior composite variable by averaging responses to six questions about routine interactions with Facebook, based on Ellison et al. [15], Marino et al. [36], and Oldmeadow et al. [41].”
MethodAssessing demand for intelligibility in context-aware applications
Lim, B. Y., & Dey, A. K. (2009) · Proceedings of the 11th international conference on Ubiquitous computing · doi:10.1145/1620545.1620576 · Cited by 246 · cited 1×
“Algorithmic transparency often refers to the act of making a system knowable or visible [18, 34, 1, 13].”
BackgroundRecommender systems — beyond matrix completion
Jannach, D., Resnick, P., Tuzhilin, A., & Zanker, M. (2016) · Communications of the ACM · doi:10.1145/2891406 · Cited by 178 · cited 2×
“Algorithms that make autonomous decisions and provide recommendations are a “mission critical” aspect of many online content and e-commerce platforms, including Facebook, Google, Netflix, and Amazon [28, 29, 39].”
BackgroundA Taxonomy for Generating Explanations in Recommender Systems
Friedrich, G., & Zanker, M. (2011) · AI Magazine · doi:10.1609/aimag.v32i3.2365 · Cited by 149 · cited 4×
“However, our explanations were not personalized to the individual preferences and characteristics of our participants, as they often are in recommender systems [20].”
BackgroundInfluentialA generalized taxonomy of explanations styles for traditional and social recommender systems
Papadimitriou, A., Symeonidis, P., & Manolopoulos, Y. (2011) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-011-0215-0 · Cited by 147 · cited 1×
“Previous research has focused on different aspects of explanations, including data sources [42, 5], cognitive fit [22], modality (e.”
BackgroundTransparency: Mediation and the Management of Visibilities
Flyverbom, M. (2016) · International journal of communication · Cited by 143
Automation, Algorithms, and Politics| Auditing for Transparency in Content Personalization Systems
Mittelstadt, B. (2016) · International journal of communication · Cited by 92
Eslami, M., Vaccaro, K., Karahalios, K., & Hamilton, K. (2017) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v11i1.14898 · Cited by 90 · cited 2×
“This could represent a feeling of violated expectations, which tends to decrease satisfaction and could result in users perceiving that their goals are not being met and that the system is unfair [11, 17].”
BackgroundA covenant with transparency: opening the black box of models
Fleischmann, K. R., & Wallace, W. A. (2005) · Communications of the ACM · doi:10.1145/1060710.1060715 · Cited by 89 · cited 1×
“Algorithmic transparency often refers to the act of making a system knowable or visible [18, 34, 1, 13].”
BackgroundHow to Recommend?: User Trust Factors in Movie Recommender Systems
Berkovsky, S., Taib, R., & Conway, D. (2017) · Proceedings of the 22nd International Conference on Intelligent User Interfaces · doi:10.1145/3025171.3025209 · Cited by 77 · cited 2×
“Explanations present information about how the system produced the recommendation and the reasons behind it [3, 24, 52], and are in service to the system’s purpose and goals [20].”
BackgroundObjective Facebook behaviour: Differences between problematic and non-problematic users
Marino, C., Finos, L., Vieno, A., Lenzi, M., & Spada, M. M. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.04.015 · Cited by 73 · cited 1×
“We created the Routine FB Behavior composite variable by averaging responses to six questions about routine interactions with Facebook, based on Ellison et al. [15], Marino et al. [36], and Oldmeadow et al. [41].”
MethodUser acceptance of knowledge-based system recommendations: Explanations, arguments, and fit
Giboney, J. S., Brown, S. A., Lowry, P. B., & Nunamaker, J. F. (2015) · Decision Support Systems · doi:10.1016/j.dss.2015.02.005 · Cited by 73 · cited 1×
“Previous research has focused on different aspects of explanations, including data sources [42, 5], cognitive fit [22], modality (e.”
BackgroundProviding awareness, explanation and control of personalized filtering in a social networking site
Nagulendra, S., & Vassileva, J. (2015) · Information Systems Frontiers · doi:10.1007/s10796-015-9577-y · Cited by 47 · cited 3×
“Algorithms that make autonomous decisions and provide recommendations are a “mission critical” aspect of many online content and e-commerce platforms, including Facebook, Google, Netflix, and Amazon [28, 29, 39].”
BackgroundKnowledgeable Explanations for Recommender Systems
Zanker, M., & Ninaus, D. (2010) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2010.131 · Cited by 41 · cited 1×
“How explanations can also increase beliefs in the competence and benevolence of a system [54] and the perceived usefulness of a system [55].”
BackgroundExamining user surprise as a symptom of algorithmic filtering
Rader, E. J. (2016) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2016.10.005 · Cited by 35
Self-citationExplaining the News Feed Algorithm: An Analysis of the "News Feed FYI" Blog
Cotter, K., Cho, J., & Rader, E. (2017) · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/3027063.3053114 · Cited by 34 · cited 2×
“They were based on a content analysis of blog posts from Facebook’s ‘News Feed FYI’ Blog through December 15, 2016 [9].”
BackgroundMethodSelf-citationFrom Invisible Algorithms to Interactive Affordances: Data After the Ideology of Machine Learning
Hogan, B. (2014) · Springer eBooks · doi:10.1007/978-3-319-05467-4_7 · Cited by 33 · cited 1×
“An algorithm is “a finite, discrete series of instructions that receive an input and produce an output” [26].”
BackgroundEnabling Accountability of Algorithmic Media: Transparency as a Constructive and Critical Lens
Diakopoulos, N. A. (2017) · Studies in big data · doi:10.1007/978-3-319-54024-5_2 · Cited by 32 · cited 4×
“Ideally, transparency mechanisms also enable users to identify biases that may result in negative consequences [13], and empower users to question and critique the system, providing grounds for demanding remediation [1].”
BackgroundInfluentialOduor, K. F., & Wiebe, E. N. (2008) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/154193120805200422 · Cited by 27 · cited 1×
“visual) [40, 21], “completeness” and “soundness” of information provided [31], and content type [24, 37].”
BackgroundPolymediated Narrative: The Case of the Supernatural Episode "Fan Fiction"
Herbig, A., & Herrmann, A. F. (2016) · International journal of communication · Cited by 26
Roles, Trust, and Reputation in Social Media Knowledge Markets
Bertino, E., & Matei, S. A. (2014) · Springer eBooks · doi:10.1007/978-3-319-05467-4 · Cited by 21
Explaining the News Feed Algorithm: An Analysis of the.
Cotter, K., Cho, J., & Rader, E. J. (2017) · Cited by 6
Self-citation
Research works printed but not linked: 4
- Association for Computing Machinery U.S. Public Policy Council. 2017. Statement on algorithmic transparency and accountability. (2017). https://www.acm.org/binaries/content/assets/public- policy/2017_usacm_statement_algorithms.pdf
- Joshua A. Kroll, Joanna Huey, Solon Barocas, Edward W. Felten, Joel R. Reidenberg, David G. Robinson, and Harlan Yu. 2016. Accountable algorithms. University of Pennsylvania Law Review 165, 3 (2016).
- Zachary C Lipton. 2016. The mythos of model interpretability. In 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016). 96-100.
- Christian Sandvig, Kevin Hamilton, Karrie Karahalios, and Cedric Langbort. 2014. Auditing algorithms: Research methods for detecting discrimination on internet platforms. Data and discrimination: converting critical concerns into productive inquiry (2014).
Cited by
Guidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439
“For example, a large body of work exists and continues to grow around how to increase transparency or explain the behaviors of AI systems (e.g., [14, 21, 23, 36, 38, 44], to name a few).”
BackgroundGenerative AI and ChatGPT: applications, challenges, and AI-human collaboration
Fui-Hoon Nah, F., Zheng, R., Cai, J., Siau, K., & Chen, L. (2023) · Journal of Information Technology Case and Application Research · doi:10.1080/15228053.2023.2233814 · Cited by 1,363
Playing the visibility game: How digital influencers and algorithms negotiate influence on Instagram
Cotter, K. (2019) · New Media & Society · doi:10.1177/1461444818815684 · Cited by 1,025
“In general, algorithms function behind the scenes with many users unaware of their presence (Eslami et al., 2015; Rader et al., 2018).”
BackgroundSelf-citationQuestioning the AI: Informing Design Practices for Explainable AI User Experiences
Liao, Q. V., Gruen, D., & Miller, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376590 · Cited by 925
Rise of Machine Agency: A Framework for Studying the Psychology of Human–AI Interaction (HAII)
Sundar, S. S. (2020) · Journal of Computer-Mediated Communication · doi:10.1093/jcmc/zmz026 · Cited by 871
Metadata
- Authors
- Rader, E., Cotter, K., & Cho, J.
- Affiliations
- Michigan State University (US)
- Venue
- Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2018-04-19
- Pages
- 1-13
- OpenAlex
- W2796133875
- Cited by
- 388
- References
- 57
- Citations by year
- 2026: 32 · 2025: 49 · 2024: 36 · 2023: 48 · 2022: 40 · 2021: 110 · 2020: 34 · 2019: 34 · 2018: 5
- FWCI
- 18.60
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Funders
- National Science Foundation (IIS-1217212)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- algorithmic transparency, explanation, transparency mechanisms, Facebook News Feed, perceived bias, user control, trust in algorithms
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.