Auditing Search Engines for Differential Satisfaction Across Demographics
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14353
- Type
- E - Conference contribution
- DOI
-
10.1145/3041021.3054197
- Title of conference / published proceedings
- Proceedings of the 26th International Conference on World Wide Web Companion, Perth, Australia, April 3-7, 2017
- First page
- 626
- Volume
- -
- Issue
- -
- ISSN
- 0000-0000
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first paper that looks into the issues of bias in search engine results based on user demographics. It shows that these primary resources of information used by may systematically underserve some groups of users. Methods based on causal inference are developed to infer user satisfaction from user behavior signals. Proposed methods are broadly applicable to evaluating bias in online services in general. The research was conducted in collaboration with Microsoft and is based on an analysis of 32M searches by 17M unique users. The work opened up a new research direction towards evaluating bias in online services.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -