Quantifying Search Bias: Investigating Sources of Bias for Political Searches in Social Media
The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Search systems in online social media sites are frequently used to find information about ongoing events and people. For topics with multiple competing perspectives, such as political events or political candidates, bias in the top ranked results significantly shapes public opinion. However, bias does not emerge from an algorithm alone. It is important to distinguish between the bias that arises from the data that serves as the input to the ranking system and the bias that arises from the ranking system itself. In this paper, we propose a framework to quantify these distinct biases and apply this framework to politics-related queries on Twitter. We found that both the input data and the ranking system contribute significantly to produce varying amounts of bias in the search results and in different ways. We discuss the consequences of these biases and possible mechanisms to signal this bias in social media search systems' interfaces.
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.
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
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
Barocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048
The political blogosphere and the 2004 U.S. election: divided they blog
Adamic, L. A., & Glance, N. (2005) · Proceedings of the 3rd international workshop on Link discovery · doi:10.1145/1134271.1134277 · Cited by 2,619 · cited 1×
“While there have been prior attempts to infer the political bias of textual content in online forums, such as blogs and news articles [1, 46, 51] or hashtags on Twitter [44], to our knowledge, no work has measured the political bias of a tweet based on its textual content, particularly due to its very small size.”
BackgroundPolitical Polarization on Twitter
Conover, M., Ratkiewicz, J., Francisco, M., Goncalves, B., Flammini, A., & Menczer, F. (2011) · Zenodo · doi:10.5281/zenodo.4589064 · Cited by 1,254
Political Polarization on Twitter
Conover, M., Ratkiewicz, J., Francisco, M., et al. (2011) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4589065 · Cited by 1,005
In Google We Trust: Users’ Decisions on Rank, Position, and Relevance
Pan, B., Hembrooke, H., Joachims, T., Lorigo, L., Gay, G., & Granka, L. (2007) · Journal of Computer-Mediated Communication · doi:10.1111/j.1083-6101.2007.00351.x · Cited by 715
Eslami, 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
Self-citationDynamic debates: an analysis of group polarization over time on Twitter
Yardi, S., & Boyd, D. (2010) · Bulletin of Science, Technology & Society · doi:10.1177/0270467610380011 · Cited by 625
Predicting the Political Alignment of Twitter Users
Conover, M. D., Goncalves, B., Ratkiewicz, J., Flammini, A., & Menczer, F. (2011) · 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing · doi:10.1109/passat/socialcom.2011.34 · Cited by 588
The search engine manipulation effect (SEME) and its possible impact on the outcomes of elections
Epstein, R., & Robertson, R. E. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1419828112 · Cited by 577
Research works printed but not linked: 4
- 10. USA Executive Office of the President. 2016. Big Data: A Report on Algorithmic Systems, Opportunity,and Civil Rights. http://tinyurl.com/Big-Data-White-House . (2016).
- 25. Amy Mitchell and Dana Page. 2015. The Evolving Role of News on Twitter and Facebook. Pew Research Center (2015).
- 34. 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).
- 39. Herman Tavani. 2014. Search Engines and Ethics. In The Stanford Encyclopedia of Philosophy (spring 2014 ed.), Edward N. Zalta (Ed.).
Cited by
Items 101–148 of 148
Berberoğlu, A., & Dinler, A. (2020) · Journal of Clinical and Experimental Investigations · doi:10.29333/jcei/9281 · Cited by 6
Urman, A., Makhortykh, M., & Hannák, A. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732026 · Cited by 16
Garcias, C. M., da Fonseca, M. N., Ferentz, L. M. D. S., & da Costa, N. S. A. R. (2021) · Liinc em Revista · doi:10.18617/liinc.v16i2.5353 · Cited by 5
Responsible Opinion Formation on Debated Topics in Web Search
Rieger, A., Draws, T., Mattis, N. M., Maxwell, D., Elsweiler, D., Gadiraju, U., McKay, D., Bozzon, A., & Pera, M. S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56066-8_32 · Cited by 12
Understanding and Mitigating Gender Bias in Information Retrieval Systems
Bigdeli, A., Arabzadeh, N., Seyedsalehi, S., Zihayat, M., & Bagheri, E. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28241-6_32 · Cited by 6
Lee, S., Nganji, J. T., & Cockburn, L. (2021) · Medicine Conflict & Survival · doi:10.1080/13623699.2021.1955759 · Cited by 5
“results, which may be influenced by a multitude of factors such as previous search history, location, and time of search (Kulshrestha et al. 2017).”
BackgroundDey, S., Duff, B. R. L., & Karahalios, K. G. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502084 · Cited by 5
Self-citationAwareness on Spread of Misinformation and its Effect on Public with Regard to COVID-19
Ramasubramanian, S., Preetha, S., Premavathy, D., & Prathap, L. (2020) · International Journal of Current Research and Review · doi:10.31782/ijcrr.2020.sp08 · Cited by 5
Pricing Risk: An XAI Analysis of Irish Car Insurance Premiums
Byrne, A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63803-9_17 · Cited by 5
Wang, G., Li, J.-Y., & Lee, Y. (2025) · Telematics and Informatics · doi:10.1016/j.tele.2025.102251 · Cited by 4
Brookhouse, A., Derr, T., Karimi, H., Bernard, H. R., & Tang, J. (2021) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3465336.3475115 · Cited by 7
“There has also been a lot of research on search bias, which is built on the idea that when searching online the results returned can be biased due to the data or the algorithms, including related to political science topics (Kulshrestha et al. 2017).”
Background(Im)balance in the Representation of News? An Extensive Study on a Decade Long Dataset from India
Chakraborty, S., Goyal, P., & Mukherjee, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19097-1_22 · Cited by 7
Machado, M. D. O. C., de Assis, E. C., de Souza, J. F., & Siqueira, S. W. M. (2024) · Anais do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.1145/3658271.3658310 · Cited by 4
“For example, the study [19] addresses biases that may exist on the Twitter platform when returning search results to its users, among other factors.”
BackgroundYang, S., Zhang, W., & Yuan, Z. (2021) · Advances in Journalism and Communication · doi:10.4236/ajc.2021.92004 · Cited by 5
“Algorithms mediate and promote content according to users’ preferences and attitudes, thereby facilitating information exchange (Kulshrestha et al., 2017).”
BackgroundMarani, A. H., Levine, J., & Baumer, E. P. S. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557410 · Cited by 4
Coupling GDPR Data Donation and Crowdsourced User Survey: A Case Study on TikTok Addiction
Yang, C., Mousavi, S., Dash, A., Gummadi, K. P., & Weber, I. G. (2024) · ACM Web Science Conference (WebSci) · doi:10.1145/3630744.3659830 · Cited by 6
“There are several ways in which researchers have so far collected such data for social media analyses– (a) APIs provided by online platforms [8, 10]; (b) web scraping from different vantage points, with user collaboration [6] or; (c) sock puppet accounts [9, 11].”
BackgroundSelf-citationLiu, J., & Azzopardi, L. A. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3661382 · Cited by 11
How AI Bots Have Reinforced Gender Bias in Hate Speech
Battista, D., & Molano, J. C. (2023) · ex aequo - Revista da Associação Portuguesa de Estudos sobre as Mulheres · doi:10.22355/exaequo.2023.48.05 · Cited by 10
“For example, in a study published in the Social Science Computer Review , some researchers reveal that they used a system learning approach to find out the language patterns that can be related to misogynistic hate speech (Kulshrestha et al .”
Investigating the Influence of Legal Case Retrieval Systems on Users' Decision Process
Wang, B., Zhang, R., Wu, Y., Ai, Q., Zhang, M., & Liu, Y. (2023) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3624918.3625321 · Cited by 2
Asuman, M. K. A., & Appiah, A. (2023) · Journal of Communications Media And Society (JOCMAS) · doi:10.63772/jocmas.v9n1.1 · Cited by 2
“The use of algorithms increases the personalised user experience of social media because users are most likely to come across communication and information adhering to their experience, interests or current location (Kulshrestha, 2017).”
Towards fair AI: a review of bias and fairness in machine intelligence
Kurumayya, V. (2025) · Journal of Computational Social Science · doi:10.1007/s42001-025-00386-8 · Cited by 4
BalancedQR: A Framework for Balanced Query Recommendation
Mishra, H., & Soundarajan, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43421-1_25 · Cited by 4
bias goggles: Graph-Based Computation of the Bias of Web Domains Through the Eyes of Users
Papadakos, P., & Konstantakis, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_52 · Cited by 3
“Furthermore, the presence of bias in media sources has been explored through human annotations [5] , by exploiting affiliations [32] , the impartiality of messages [33] , the content and linked-based tracking of topic bias [22] , and the quantification of data and algorithmic bias [19] .”
BackgroundDlamini, P., & Mbatha, B. (2023) · Commonwealth Youth and Development · doi:10.25159/2663-6549/11496 · Cited by 1
How affect shapes online information seeking about political actors
Puschmann, C., Rauxloh, H., Merten, L., Stier, S., Weller, K., & Kulshrestha, J. (2025) · New Media & Society · doi:10.1177/14614448251346199 · Cited by 4
“…Urman and Makhortykh, 2023) and examined inconsistency and the (non)representation of issues in search engine results in response to politically salient search queries (Courtois et al., 2018; Kravets and Toepfl, 2022; Kulshrestha et al., 2017; Makhortykh and Wijermars, 2023; Steiner et al., 2022).”
Self-citationRecommender Systems on the Online Entertainment Industry: From Metrics to Ethics
Sotero, J. M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/406031 · Cited by 1
Protect the Filter Bubbles: Emphasizing User Speech Rights in Algorithmically Curated Online Forums
Dames, P. (2021) · UF Journal of Undergraduate Research · doi:10.32473/ufjur.v23i.128414 · Cited by 1
“There is also the concern of bias in Twitter search results for politics-related queries (Kulshrestha et al., 2017).”
Effectual Seed Pick Framework Focusing on Maximizing Influence in Social Networks
Choudhary, S., Sharma, K., & Bajaj, M. (2023) · Wireless Communications and Mobile Computing · doi:10.1155/2023/3185391 · Cited by 2
Evaluating Cognitive Biases in Conversational and Generative IIR: A Tutorial
Azzopardi, L. A., & Liu, J. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698437 · Cited by 4
Fairness in Unsupervised Learning
Deepak, P., Jose, J. M., & Sanil, V. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3412175 · Cited by 2
Crowdsourcing Data To Visualize Potential Hotspots For Covid-19 Active Cases In Indonesia
Rahardjo, N., Santosa, D. H., & Marhaento, H. (2021) · GEOGRAPHY ENVIRONMENT SUSTAINABILITY · doi:10.24057/2071-9388-2021-011 · Cited by 1
“Social media platforms such as Facebook, Instagram, and Twitter have provided direct access to account users’ preferences and attitudes, algorithms mediate, and facilitate content promotion (Kulshrestha et al. 2017).”
BackgroundKeyword Recommendation for Fair Search
Mishra, H., & Soundarajan, S. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-09316-6_12 · Cited by 1
“[Juhi Kulshrestha and Gummadi, 2017] observed search bias in rankings, and proposed a framework to measure the bias of the results of a search engine.”
Backgroundvan Woudenberg, T. J., Buijzen, M., Hendrikx, R. J. P., van Weert, J. C. M., van den Putte, B., Kroese, F. M., Bouman, M. P. A., de Bruin, M., & Lambooij, M. (2022) · JMIR Infodemiology · doi:10.2196/33713 · Cited by 2
Nelimarkka, M., & Vuorenmaa, V. (2024) · Research Square · doi:10.21203/rs.3.rs-4162467/v1 · Cited by 2
On Epistemic Diversity in Large Language Models
Kirsten, E., Krämer, N., & Zafar, M. B. (2026) · arXiv · doi:10.48550/arxiv.2609.04835
“Another line of work examines whether models reflect a balanced range of political viewpoints (Kulshrestha et al., 2017; Peters, 2022).”
Self-citationvan Woudenberg, T. J., Buijzen, M., Hendrikx, R. J. P., van Weert, J. C. M., van den Putte, B., Kroese, F. M., Bouman, M. P. A., de Bruin, M., & Lambooij, M. (2021) · doi:10.2196/preprints.33713
Maillé, P., & Tuffin, B. (2022) · Springer eBooks · doi:10.1007/978-3-031-06271-1_7
The Evolution of Information Seeking Practices and Technologies and the Future of the Library
Wan, S. Y. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95689-5.00238-8
Kaz-Onyeakazi, I. A. (2025) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2443120
When will Google defend democracy?
Robertson, R. E. (2018) · doi:10.64628/aai.4jmdpxq9p
Habib, H., Stoldt, R., High, A. C., Ekdale, B., Peterson, A., Biddle, K., Ssozi, J., & Nithyanand, R. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757656 · Cited by 6
“In contrast, Kulshesta et al. [56] investigated the source of bias in search results on social media platforms, such as Twitter, and found the content library to play a significant role in shaping bias in search results.”
Factors influencing nurses’ susceptibility to online health misinformation: evidence from GreecePreprint
Katsiroumpa, A., Moisoglou, I., Konstantakopoulou, O., & Galanis, P. (2025) · medRxiv · doi:10.1101/2025.11.19.25340604
Human-Centered and Participatory AI Auditing
Deng, W. H., Holstein, K., & Eslami, M. (2026) · Springer eBooks · doi:10.1007/978-981-97-8440-0_102-1 · Cited by 1
Self-citationHuman-Centered and Participatory AI Auditing
Deng, W. H., Holstein, K., & Eslami, M. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_102 · Cited by 1
Self-citationRogers, C., Alqadri, A., Beaton, F., & Moshfeghi, Y. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808546
FairTopk: Efficient and Flexible Fairness-Aware Top-k Ranking
Liebrand, N. A., & Conrad, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37654-1_22
Katsiroumpa, A., Moisoglou, I., Konstantakopoulou, O., & Galanis, P. (2026) · International Nursing Review · doi:10.1111/inr.70235 · Cited by 1
“Algorithms, designed to reflect user preferences and attitudes, facilitate the promotion and circulation of content, thereby accelerating information spread (Kulshrestha et al. 2017 ).”
Liu, Y., & Yue, Z. (2026) · JMIR Infodemiology · doi:10.2196/79434
“At the same time, these same features can accelerate the spread of misinformation, amplify unverified claims, and make misleading information appear credible through repetition, engagement, and social endorsement [4-6].”
Metadata
- Authors
- Kulshrestha, J., Eslami, M., Messias, J., Zafar, M. B., Ghosh, S., Gummadi, K. P., & Karahalios, K.
- Affiliations
- Max Planck Institute for Software Systems (DE)
- University of Illinois Urbana-Champaign (US)
- Indian Institute of Engineering Science and Technology, Shibpur (IN)
- ORCID
- Venue
- Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing
- Publisher
- ACM
- Published
- 2017-02-25
- Pages
- 417-432
- OpenAlex
- W4300539796
- Cited by
- 148
- References
- 45
- Citations by year
- 2026: 7 · 2025: 9 · 2024: 15 · 2023: 18 · 2022: 21 · 2021: 28 · 2020: 16 · 2019: 15 · 2018: 15 · 2017: 4
- FWCI
- 10.50
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Computer Supported Cooperative Work (CSCW) (publishedVersion)
- Funders
- NSF (CHS-1564041)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- search bias, social media search, ranking bias, data bias, Twitter, search result ranking, public opinion, bias quantification
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.