Search for: All records

Algorithmic fairness in the context of personalized recommendation presents significantly different challenges to those commonly encountered in classification tasks. Researchers studying classification have generally considered fairness to be a matter of achieving equality of outcomes (or some other metric) between a protected and unprotected group, and built algorithmic interventions on this basis. We argue that fairness in real-world application settings in general, and especially in the context of personalized recommendation, is much more complex and multi-faceted, requiring a more general approach. To address the fundamental problem of fairness in the presence of multiple stakeholders, with different definitions of fairness, we propose the Social Choice for Recommendation Under Fairness – Dynamic (SCRUF-D) architecture, which formalizes multistakeholder fairness in recommender systems as a two-stage social choice problem. In particular, we express recommendation fairness as a combination of an allocation and an aggregation problem, which integrate both fairness concerns and personalized recommendation provisions, and derive new recommendation techniques based on this formulation. We demonstrate the ability of our framework to dynamically incorporate multiple fairness concerns using both real-world and synthetic datasets. 

The benefits of service learning in computer and information science (CIS) are believed to be significant, ranging from providing students with real-world experiences to retaining students to positively impacting community partners. Although there are many benefits of service learning, the CIS domain does impose unique costs for integrating service learning into the curriculum. Yet there is little systematic research to help the CIS community understand best practices for maximizing benefits while minimizing costs. Experience reports about service learning courses in CIS have appeared in the literature annually since 2000, and thus we address this gap in knowledge by conducting a systematic review and content analysis of 84 experience reports from theThe ACM Guide to Computing Literature. We synthesize the current state of service learning in CIS as well as derive recommendations for best practices and future research directions. 

Recommender systems have a variety of stakeholders. Applying concepts of fairness in such systems requires attention to stakeholders’ complex and often-conflicting needs. Since fairness is socially constructed, there are numerous definitions, both in the social science and machine learning literatures. Still, it is rare for machine learning researchers to develop their metrics in close consideration of their social context. More often, standard definitions are adopted and assumed to be applicable across contexts and stakeholders. Our research starts with a recommendation context and then seeks to understand the breadth of the fairness considerations of associated stakeholders. In this paper, we report on the results of a semi-structured interview study with 23 employees who work for the Kiva microlending platform. We characterize the many different ways in which they enact and strive toward fairness for microlending recommendations in their own work, uncover the ways in which these different enactments of fairness are in tension with each other, and identify how stakeholders are differentially prioritized. Finally, we reflect on the implications of this study for future research and for the design of multistakeholder recommender systems. 

Service learning—an educational experience in which students provide service to a community partner while learning content knowledge, professional skills, and critical thinking—can provide significant benefits to students and the community. We present survey results from 227 postsecondary students in computing to provide insights into their attitudes toward service learning, and how these relate to course-taking motivations and sense of civic duty. Based on the survey results, we argue that service learning should be required in an undergraduate computing major. However, we problematize this provocation based on three types of pitfalls: courses that do not prepare students to understand social contexts in which technical solutions are promoted, lack of resources for faculty teaching the courses, and the potential to harm both community partners and students.