Search

This systematic review synthesizes current research on echo chambers and filter bubbles to highlight the reasons for the dissent in echo chamber research on the existence, antecedents, and effects of the phenomenon. The review of 112 studies reveals that the lack of consensus in echo chamber research is based on different conceptualizations and operationalizations of echo chambers. While studies that have conceptualized echo chambers with homophily and utilized data-driven computational social science (CSS) methods have confirmed the echo chamber hypothesis and polarization effects in social media, content exposure studies and surveys that have explored the full spectrum of media exposure have rejected it. Most of these studies have been conducted in the United States, and the review emphasizes the need for a more comprehensive understanding of how echo chambers work in systems with more than two parties and outside the Global North. To advance our understanding of this phenomenon, future research should prioritize conducting more cross-platform studies, considering algorithmic filtering changes through continuous auditing, and examining the causal direction of the association between polarization, fragmentation, and the establishment of online echo chambers. The review also provides the advantages and disadvantages of different operationalizations and makes recommendations for studies in the European Union (EU), which will become possible with the upcoming Digital Services Act (DSA). Overall, this systematic review contributes to the ongoing scholarly discussion on the existence, antecedents, and effects of echo chambers and filter bubbles.

Online platforms face the challenge of moderating an ever-increasing volume of content, including harmful hate speech. In the absence of clear legal definitions and a lack of transparency regarding the role of algorithms in shaping decisions on content moderation, there is a critical need for external accountability. Our study contributes to filling this gap by systematically evaluating four leading cloud-based content moderation services through a third-party audit, highlighting issues such as biases against minorities and vulnerable groups that may arise through over-reliance on these services. Using a black-box audit approach and four benchmark data sets, we measure performance in explicit and implicit hate speech detection as well as counterfactual fairness through perturbation sensitivity analysis and present disparities in performance for certain target identity groups and data sets. Our analysis reveals that all services had difficulties detecting implicit hate speech, which relies on more subtle and codified messages. Moreover, our results point to the need to remove group-specific bias. It seems that biases towards some groups, such as Women, have been mostly rectified, while biases towards other groups, such as LGBTQ+ and PoC remain., Comment: Accepted at European Workshop on Algorithmic Fairness (EWAF'24)

The European legislature has proposed the Digital Services Act (DSA) and Artificial Intelligence Act (AIA) to regulate platforms and Artificial Intelligence (AI) products. We review to what extent third-party audits are part of both laws and to what extent access to models and data is provided. By considering the value of third-party audits and third-party data access in an audit ecosystem, we identify a regulatory gap in that the Artificial Intelligence Act does not provide access to data for researchers and civil society. Our contributions to the literature include: (1) Defining an AI audit ecosystem that incorporates compliance and oversight. (2) Highlighting a regulatory gap within the DSA and AIA regulatory framework, preventing the establishment of an AI audit ecosystem. (3) Emphasizing that third-party audits by research and civil society must be part of that ecosystem and demand that the AIA include data and model access for certain AI products. We call for the DSA to provide NGOs and investigative journalists with data access to platforms by delegated acts and for adaptions and amendments of the AIA to provide third-party audits and data and model access at least for high-risk systems to close the regulatory gap. Regulations modeled after European Union AI regulations should enable data access and third-party audits, fostering an AI audit ecosystem that promotes compliance and oversight mechanisms.

The purpose of regulatory data minimization obligations is to limit personal data to the absolute minimum necessary for a given context. Beyond the initial data collection, storage, and processing, data minimization is also required for subsequent data releases, as it is the case when data are provided using query-capable Web APIs. Data-providing Web APIs, however, typically lack sophisticated data minimization features, leaving the task open to manual and all too often missing implementations. In this paper, we address the problem of data minimization for data-providing, query-capable Web APIs. Based on a careful analysis of functional and non-functional requirements, we introduce Janus, an easy-to-use, highly configurable solution for implementing legally compliant data minimization in GraphQL Web APIs. Janus provides a rich set of information reduction functionalities that can be configured for different client roles accessing the API. We present a technical proof-of-concept along with experimental measurements that indicate reasonable overheads. Janus is thus a practical solution for implementing GraphQL APIs in line with the regulatory principle of data minimization., Comment: Preprint version (2022-03-18) This version of the contribution has been accepted for publication at the 22nd International Conference on Web Engineering (ICWE 2022), Bari, Italy