Visibility Allocation Systems: How Algorithmic Design Shapes Online Visibility and Societal Outcomes
Stefania Ionescu, Robin Forsberg, Elsa Lichtenegger, Salima Jaoua, Kshitijaa Jaglan, Florian Dorfler, Aniko Hannak
TL;DR
The paper addresses the challenge of understanding and evaluating visibility allocation systems (VASs), complex semi-automated pipelines that decide which processed data to present to users. It proposes a formal framework that decomposes VASs into modular tools (e.g., filter, sort, moderation, forecasting) and represents them with data-flow diagrams (DFDs) to connect design choices to long-term societal effects. Key contributions include formal definitions of VASs and their tools, an adapted DFD methodology for sociotechnical analysis, a metrics ecosystem for multi-stakeholder evaluation, and a school-choice case study demonstrating executable representations and avenues for cross-domain learning. The work aims to support researchers and policymakers by enhancing transparency, enabling auditable documentation, and enabling adaptive compliance in high-risk settings through an integrated simulation environment.
Abstract
Throughout application domains, we now rely extensively on algorithmic systems to engage with ever-expanding datasets of information. Despite their benefits, these systems are often complex (comprising of many intricate tools, e.g., moderation, recommender systems, prediction models), of unknown structure (due to the lack of accompanying documentation), and having hard-to-predict yet potentially severe downstream consequences (due to the extensive use, systematic enactment of existing errors, and many comprising feedback loops). As such, understanding and evaluating these systems as a whole remains a challenge for both researchers and legislators. To aid ongoing efforts, we introduce a formal framework for such visibility allocation systems (VASs) which we define as (semi-)automated systems deciding which (processed) data to present a human user with. We review typical tools comprising VASs and define the associated computational problems they solve. By doing so, VASs can be decomposed into sub-processes and illustrated via data flow diagrams. Moreover, we survey metrics for evaluating VASs throughout the pipeline, thus aiding system diagnostics. Using forecasting-based recommendations in school choice as a case study, we demonstrate how our framework can support VAS evaluation. We also discuss how our framework can support ongoing AI-legislative efforts to locate obligations, quantify systemic risks, and enable adaptive compliance.