Exploring author gender in book rating and recommendation

Abstract

Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of the patterns in rating datasets reflect important real-world differences between the various users and items in the data; other patterns may be irrelevant or possibly undesirable for social or ethical reasons, particularly if they reflect undesired discrimination, such as gender or ethnic discrimination in publishing. In this work, we examine the response of collaborative filtering recommender algorithms to the distribution of their input data with respect to a dimension of social concern, namely content creator gender. Using publicly-available book ratings data, we measure the distribution of the genders of the authors of books in user rating profiles and recommendation lists produced from this data. We find that common collaborative filtering algorithms differ in the gender distribution of their recommendation lists, and in the relationship of that output distribution to user profile distribution.

Fairness in Recommendation Ranking through Pairwise Comparisons

“…As discussed previously, a wide variety of fairness concerns have been highlighted in the literature. In this work, we primarily focus on the risk to groups of items from being under-recommended [21,8,39,45]. For example, if a social network under-ranked posts by a given demographic group, that could limit the group's visibility and thus engagement on the service.…”

“…Recommenders are pivotal in connecting users to relevant content, items or information throughout the web, but with both users and content producers, sellers or information providers relying on these systems, it is important that we understand who is being supported and who is not. In this paper we focus on the risk of a recommender system under-ranking groups of items [21,8,39]. For example, if a social network under-ranked posts by a given demographic group, that could limit the group's visibility on the service.…”

Fairness and discrimination in recommendation and retrieval

“…The issues of fairness, accountability, transparency, bias, discrimination, justice, and ethics that are seeing increased attention in many areas of computing also have signifcant relevance to the information retrieval community [3,8,9,12]. There is a substantial and rapidly-growing research literature studying fairness, bias, and discrimination in general machine learning contexts [5].…”

Investigating the lack of diversity in user behavior: The case of musical content on online platforms

“…These issues are all at the core of intense debates and relate to many different contexts ranging from the exploitation of private data [8] to the impact of search engines on elections [9,10], the dissemination of fake news [11], and filter bubble phenomena on social media [12]. Consequently, this increasing use of digital platforms and their recommendation systems has led the scientific community to focus on the impact of algorithmic decisions on users' behavior [2,13,14,15,16].…”

“…The importance of this question is reflected in the emergence of intense scientific activity dedicated to analyzing the diversity of information proposed to users [15,22], particularly in the context of music recommendation systems [23,24,25,26,27,28,29] which is the context of our validation settings. Indeed, whether to provide purchasing recommendations (i.e., the suggestion to purchase an item on Amazon) or information recommendations (i.e., the suggestion to read a post in Newsfeed or listen to a song on Spotify), algorithms strongly affect what is made visible to users.…”