On the negative impact of social influence in recommender systems: A study of bribery in collaborative hybrid algorithms

Robust reputation independence in ranking systems for multiple sensitive attributes

Ranking systems have an unprecedented influence on how and what information people access, and their impact on our society is being analyzed from different perspectives, such as users’ discrimination. A notable example is represented by reputation-based ranking systems, a class of systems that rely on users’ reputation to generate a non-personalized item-ranking, proved to be biased against certain demographic classes. To safeguard that a given sensitive user’s attribute does not systematically affect the reputation of that user, prior work has operationalized a reputation independence constraint on this class of systems. In this paper, we uncover that guaranteeing reputation independence for a single sensitive attribute is not enough. When mitigating biases based on one sensitive attribute (e.g., gender), the final ranking might still be biased against certain demographic groups formed based on another attribute (e.g., age). Hence, we propose a novel approach to introduce reputation independence for multiple sensitive attributes simultaneously. We then analyze the extent to which our approach impacts on discrimination and other important properties of the ranking system, such as its quality and robustness against attacks. Experiments on two real-world datasets show that our approach leads to less biased rankings with respect to multiple users’ sensitive attributes, without affecting the system’s quality and robustness.

Trespassing the gates of research: identifying algorithmic mechanisms that can cause distortions and biases in academic social media

Purpose

The use of recommender systems is increasing on academic social media (ASM). However, distinguishing the elements that may be influenced and/or exert influence over content that is read and disseminated by researchers is difficult due to the opacity of the algorithms that filter information on ASM. In this article, the purpose of this paper is to investigate how algorithmic mediation through recommender systems in ResearchGate may uphold biases in scholarly communication.

Design/methodology/approach

The authors used a multi-method walkthrough approach including a patent analysis, an interface analysis and an inspection of the web page code.

Findings

The findings reveal how audience influences on the recommendations and demonstrate in practice the mutual shaping of the different elements interplaying within the platform (artefact, practices and arrangements). The authors show evidence of the mechanisms of selection, prioritization, datafication and profiling. The authors also substantiate how the algorithm reinforces the reputation of eminent researchers (a phenomenon called the Matthew effect). As part of defining a future agenda, we discuss the need for serendipity and algorithmic transparency.

Research limitations/implications

Algorithms change constantly and are protected by commercial secrecy. Hence, this study was limited to the information that was accessible within a particular period. At the time of publication, the platform, its logic and its effects on the interface may have changed. Future studies might investigate other ASM using the same approach to distinguish potential patterns among platforms.

Originality/value

Contributes to reflect on algorithmic mediation and biases in scholarly communication potentially afforded by recommender algorithms. To the best of our knowledge, this is the first empirical study on automated mediation and biases in ASM.

Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations

Online education platforms play an increasingly important role in mediating the success of individuals’ careers. Therefore, while building overlying content recommendation services, it becomes essential to guarantee that learners are provided with equal recommended learning opportunities, according to the platform principles, context, and pedagogy. Though the importance of ensuring equality of learning opportunities has been well investigated in traditional institutions, how this equality can be operationalized in online learning ecosystems through recommender systems is still under-explored. In this paper, we shape a blueprint of the decisions and processes to be considered in the context of equality of recommended learning opportunities, based on principles that need to be empirically-validated (no evaluation with live learners has been performed). To this end, we first provide a formalization of educational principles that model recommendations’ learning properties, and a novel fairness metric that combines them to monitor the equality of recommended learning opportunities among learners. Then, we envision a scenario wherein an educational platform should be arranged in such a way that the generated recommendations meet each principle to a certain degree for all learners, constrained to their individual preferences. Under this view, we explore the learning opportunities provided by recommender systems in a course platform, uncovering systematic inequalities. To reduce this effect, we propose a novel post-processing approach that balances personalization and equality of recommended opportunities. Experiments show that our approach leads to higher equality, with a negligible loss in personalization. This paper provides a theoretical foundation for future studies of learners’ preferences and limits concerning the equality of recommended learning opportunities.

A time-sensitive model to predict topic popularity in news providers1

The volume of news increases everyday, triggering competition for users’ attention. Predicting which topics will become trendy has many applications in domains like marketing or politics, where it is crucial to anticipate how much interest a product or a person will attract. We propose a model for representing topic popularity behavior across time and to predict if a topic will become trendy in the future. Furthermore, we tested our proposal on a real data set from Yahoo News and analyzed the performance of various classifiers for the topic popularity prediction task. Experiments confirmed the validity of the proposed model.