Auditing Search Engines for Differential Satisfaction Across Demographics
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Many online services, such as search engines, social media platforms, and digital marketplaces, are advertised as being available to any user, regardless of their age, gender, or other demographic factors. However, there are growing concerns that these services may systematically underserve some groups of users. In this paper, we present a framework for internally auditing such services for differences in user satisfaction across demographic groups, using search engines as a case study. We first explain the pitfalls of naively comparing the behavioral metrics that are commonly used to evaluate search engines. We then propose three methods for measuring latent differences in user satisfaction from observed differences in evaluation metrics. To develop these methods, we drew on ideas from the causal inference literature and the multilevel modeling literature. Our framework is broadly applicable to other online services, and provides general insight into interpreting their evaluation metrics.
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
Barocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048 · cited 1×
“From a public-relations perspective, service providers and the decisions made by their services are under increasing scrutiny by journalists [13] and civil-rights enforcement [38, 4] for seemingly unfair behavior.”
BackgroundEquality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 1×
“Other work sought to detect unfairness through reverse A/B testing with synthetic users [31, 12], algorithmic auditing [37], and analysis of predictions made by supervised machine learning methods [24].”
MethodCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 1×
“Although machine learning can address many challenges in web search, there is also increasing evidence that suggests that these methods may systematically and in-conspicuously underserve some groups of users [7, 3].”
BackgroundDatta, A., Sen, S., & Zick, Y. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.42 · Cited by 728
Measuring personalization of web search
Hannak, A., Sapiezynski, P., Molavi Kakhki, A., Krishnamurthy, B., Lazer, D., Mislove, A., & Wilson, C. (2013) · Proceedings of the 22nd international conference on World Wide Web · doi:10.1145/2488388.2488435 · Cited by 396
Auditing black-box models for indirect influence
Adler, P., Falk, C., Friedler, S. A., Nix, T., Rybeck, G., Scheidegger, C., Smith, B., & Venkatasubramanian, S. (2018) · Knowledge and Information Systems · doi:10.1007/s10115-017-1116-3 · Cited by 280
Auditing Black-Box Models for Indirect Influence
Adler, P., Falk, C., Friedler, S. A., Rybeck, G., Scheidegger, C., Smith, B., & Venkatasubramanian, S. (2016) · 2016 IEEE 16th International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2016.0011 · Cited by 280
Who uses web search for what: and how
Weber, I., & Jaimes, A. (2011) · Proceedings of the fourth ACM international conference on Web search and data mining · doi:10.1145/1935826.1935839 · Cited by 91 · cited 1×
“…in various settings: Ford et al. [18] conducted a controlled experiment involving masters students, varying age and gender; Weber and Castillo [40, 41] studied differences in user behavior using search log data; Bi et al. [6] demonstrated that search behavior can be used to predict demographic…”
MethodSunlight: Fine-grained Targeting Detection at Scale with Statistical Confidence
Lecuyer, M., Spahn, R., Spiliopolous, Y., Chaintreau, A., Geambasu, R., & Hsu, D. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813614 · Cited by 48 · cited 1×
“Other work sought to detect unfairness through reverse A/B testing with synthetic users [31, 12], algorithmic auditing [37], and analysis of predictions made by supervised machine learning methods [24].”
Method
Research works printed but not linked: 32
- H. Ajutsu, G. E. Legge, J. A. Ross, and K. J. Scheubel. Psychophysics of reading--X. Effects of age-related changes in vision. Journal of Gerontology, 46(6):325--331, 1991. · DOI · Paper page
- P. N. Bennett, K. Svore, and S. T. Dumais. Classification-enhanced ranking. In WWW, 2010. · DOI · Paper page
- B. Bin, M. Shokouhi, M. Kosinski, and T. Graepel. Inferring the demographics of search users: Social data meets search queries. In WWW, 2013. · DOI · Paper page
- A. Borisov, I. Markov, M. de Rijke, and P. Serdyukov. A context-aware time model for web search. In SIGIR, 2016. · DOI
- G. Buscher, L. van Elst, and A. Dengel. Segment-level time as implicit feedback: A comparison to eye tracking. In SIGIR, 2009. · DOI
- B. Carterette, E. Kanoulas, and E. Yilmaz. Incorporating variability in user behavior into systems based evaluation. In CIKM, 2012. · doi:10.1145/2396761.2396782
- S. L. Connelly, L. Hasher, and R. T. Zacks. Age and reading: The impact of distraction. Psychology and Aging, 6(4):533--541, 1991. · DOI · Paper page
- N. Diakopoulos. Algorithmic accountability. Digital Journalism, 3(3):398--415, 2015. · DOI · Paper page
- D. Downey, S. Dumais, and E. Horvitz. Heads and tails: Studies of web search with common and rare queries. In SIGIR, 2007. · doi:10.1145/1277741.1277939
- R. Epstein and R. E. Robertson. The search engine manipulation effect (SEME) and its possible impact on the outcomes of elections. PNAS, 2015. · DOI · Paper page
- H. A. Feild, J. Allan, and R. Jones. Predicting searcher frustration. In SIGIR, 2010. · DOI · Paper page
- N. Ford, D. Miller, and N. Moss. Web search strategies and human individual differences: Cognitive and demographic factors, internet attitudes, and approaches. JASIST, 56(7):741--756, 2005. · DOI
- G. M. Fulgoni. The "professional respondent" problem in online survey panels today. Presented at the Marketing Research Association Annual Conference, 2005.
- A. Gelman, J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari, and D. B. Rubin. Bayesian Data Analysis. CRC Press, 2014. · doi:10.1201/b16018 · Paper page
- A. Gelman and J. Hill. Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press, 2006. · DOI · Paper page
- A. Hassan, X. Shi, N. Craswell, and B. Ramsey. Beyond clicks: Query reformulation as a predictor of search satisfaction. In CIKM, 2013. · DOI · Paper page
- A. Hassan and R. W. White. Personalized models of search satisfaction. In CKIM, 2013. · DOI
- Y. Hu, Y. Koren, and C. Volinsky. Collaborative filtering for implicit feedback datasets. In ICDM, 2008. · DOI · Paper page
- J. Jiang, A. Hassan, Z. Shi, and R. W. White. Understanding and predicting graded search satisfaction. In WSDM, 2015. · DOI
- Y. Kim, A. Hassan, R. W. White, and I. Zitouni. Modeling dwell time to predict click-level satisfaction. In WSDM, 2014. · DOI · Paper page
- A. Large, J. Beheshti, and T. Rahman. Gender differences in collaborative web searching behavior: An elementary school study. Information Processing and Management, 2002. · DOI · Paper page
- L. Lorigo, B. Pan, H. Hembrooke, T. Joachims, L. Granka, and G. Gay. The influence of task and gender on search and evaluation behavior using Google. Information Processing and Management, 2006. · DOI · Paper page
- E. R. Núnez-Valdéz, J. M. C. Lovelle, O. S. Martínez, V. García-Díaz, P. O. de Pablos, and C. Marín. Implicit feedback techniques on recommender systems applied to electronic books. Computers in Human Behavior, 28(4):1186--1193, 2012. · DOI
- F. Radlinski, M. Szummer, and N. Craswell. Inferring query intent from reformulations and clicks. In WWW, 2010. · doi:10.1145/1772690.1772859
- M. Roy and M. T. H. Chi. Gender differences in patterns of searching the web. Journal of Educational Computing Research, 29(3), 2003. · DOI
- D. B. Rubin. Matched Sampling for Causal Effects. Cambridge University Press, 2006. · DOI · Paper page
- Y. Wang and E. Agichtein. Query ambiguity revisited: Clickthrough measures for distinguishing informational and ambiguous queries. In NAACL, 2010.
- I. Weber and C. Castillo. The demographics of web search. In SIGIR, 2010. · DOI · Paper page
- R. W. White. Interactions with Search Systems. Cambridge University Press, 2016. · DOI · Paper page
- R. W. White and S. Dumais. Characterizing and predicting search engine switching behavior. In CIKM, 2009. · DOI
- P. Yin, P. Luo, W.-C. Lee, and M. Wang. Silence is also evidence: Interpreting dwell time for recommendation from psychological perspective. In KDD, 2013. · DOI
- M. Zhou. Gender difference in web search perceptions and behavior: Does it vary by task performance? Computers and Education, 78:174--184, 2014. · DOI
Cited by
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kiciman, E. (2016) · doi:10.2139/ssrn.2886526 · Cited by 763
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kıcıman, E. (2019) · Frontiers in Big Data · doi:10.3389/fdata.2019.00013 · Cited by 763
“Moreover, these surrogate objectives themselves might also be based on imprecise measurement or biased modeling (Mehrotra et al., 2017), and have the potential to create self-fulfilling feedback loops when decisions are made based on the inference results and the outcomes are fed back into the models as training data…”
BackgroundSelf-citationEquity of Attention: Amortizing Individual Fairness in Rankings
Biega, A. J., Gummadi, K. P., & Weikum, G. (2018) · The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval · doi:10.1145/3209978.3210063 · Cited by 337
Evaluating Recommender Systems: Survey and Framework
Zangerle, E., & Bauer, C. (2023) · ACM Computing Surveys · doi:10.1145/3556536 · Cited by 283
Mehrotra, R., McInerney, J., Bouchard, H., Lalmas, M., & Diaz, F. (2018) · Proceedings of the 27th ACM International Conference on Information and Knowledge Management · doi:10.1145/3269206.3272027 · Cited by 279
Self-citation
Metadata
- Authors
- Mehrotra, R., Anderson, A., Diaz, F., Sharma, A., Wallach, H., & Yilmaz, E.
- Venue
- Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion
- Publisher
- ACM Press
- Published
- 2017
- Pages
- 626-633
- OpenAlex
- W2612327332
- Cited by
- 68
- References
- 10
- FWCI
- 5.29
- Type
- conference paper
- Language
- en
- Open access
- gold
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.