FairSearch: a tool for fairness in ranked search results

Zehlike, Meike; Sühr, Tom; Castillo, Carlos; Kitanovski, Ivan

doi:http://dx.doi.org/10.1145/3366424.3383534

FairSearch: a tool for fairness in ranked search results

License

Citation

Zehlike M, Sühr T, Castillo C, Kitanovski I. FairSearch: a tool for fairness in ranked search results. In: Seghrouchni AEF, Sukthankar G, Liu TY, van Steen M. WWW '20: Companion Proceedings of the Web Conference; 2020 Apr 20-24; Taipei, Taiwan. New York: Association for Computing Machinery; 2020. p. 172-75. DOI: 10.1145/3366424.3383534

Abstract

Ranked search results and recommendations have become the main mechanism by which we find content, products, places, and people online. With hiring, selecting, purchasing, and dating being increasingly mediated by algorithms, rankings may determine business opportunities, education, access to benefits, and even social success. It is therefore of societal and ethical importance to ask whether search results can demote, marginalize, or exclude individuals of unprivileged groups or promote products with undesired features. In this paper we present FairSearch, the first fair open source search API to provide fairness notions in ranked search results. We implement two well-known algorithms from the literature, namely FA*IR (Zehlike et al., 9) and DELTR (Zehlike and Castillo, 10) and provide them as stand-alone libraries in Python and Java. Additionally we implement interfaces to Elasticsearch for both algorithms, a well-known search engine API based on Apache Lucene. The interfaces use the aforementioned Java libraries and enable search engine developers who wish to ensure fair search results of different styles to easily integrate DELTR and FA*IR into their existing Elasticsearch environment.