A Multistakeholder Approach to Value-Driven Co-Design of Recommender System Evaluation Metrics in Digital Archives

Abstract

This paper presents the first multistakeholder approach for translating diverse stakeholder values into an evaluation metric setup for Recommender Systems (RecSys) in digital archives. While commercial platforms mainly rely on engagement metrics, cultural heritage domains require frameworks that balance competing priorities among archivists, platform owners, researchers, and other stakeholders. To address this challenge, we conducted high-profile focus groups (5 groups x 5 persons) with upstream, provider, system, consumer, and downstream stakeholders, identifying value priorities across critical dimensions: visibility/representation, expertise adaptation, and transparency/trust. Our analysis shows that stakeholder concerns naturally align with four sequential research funnel stages: discovery, interaction, integration, and impact. The resulting evaluation setup addresses domain-specific challenges including collection representation imbalances, non-linear research patterns, and tensions between specialized expertise and broader accessibility. We propose directions for tailored metrics in each stage of this research journey, such as research path quality for discovery, contextual appropriateness for interaction, metadata-weighted relevance for integration, and cross-stakeholder value alignment for impact assessment. Our contributions extend beyond digital archives to the broader RecSys community, offering transferable evaluation approaches for domains where value emerges through sustained engagement rather than immediate consumption.

Accepted at RecSys 2025

References in corpus (11)

• Robust Speech Recognition via Large-Scale Weak Supervision
• Fairness in Recommender Systems: Research Landscape and Future Directions
• A Survey on Popularity Bias in Recommender Systems
• Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
• Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities
• Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations
• Value Identification in Multistakeholder Recommender Systems for Humanities and Historical Research: The Case of the Digital Archive Monasterium.net
• A Worrying Reproducibility Study of Intent-Aware Recommendation Models
• De-centering the (Traditional) User: Multistakeholder Evaluation of Recommender Systems
• Challenges in Implementing a Recommender System for Historical Research in the Humanities
• Joint Modeling in Recommendations: A Survey