Ranking Companion: A Visual Analytics Approach to Item-Based Ranking with Hybrid Item Selection
2026-06-22 • Human-Computer Interaction
Human-Computer InteractionInformation Retrieval
AI summaryⓘ
The authors address the difficulty of creating personalized item rankings when users can't easily describe their preferences using data attributes. They developed Ranking Companion, a tool that helps users pick items they like directly to build rankings, instead of relying only on item attributes. This tool uses a combination of six different item-selection methods and machine learning to generate rankings and explain them to users. In tests with 10 people, the authors found that each method offers different benefits like accuracy or diversity, and combining them helps improve user control and satisfaction.
personalized rankingitem-based rankingactive learningitem-selection methodsvisual analyticsmachine learninguser studylistwise preferencesranking modeldata attributes
Authors
Aman Kumar, Maximilian Tornow, Michaela Benk, Ibrahim Al-Hazwani, Jürgen Bernard
Abstract
Personalizing item ranking creation is a challenging task, especially when users lack knowledge of data attributes or the ability to express and formalize their attribute preferences. Item-based ranking creation is an approach allowing users to directly externalize preferences through known-item judgments rather than attribute-based scoring. However, a core challenge of item-based ranking is identifying and selecting representative candidate items for externalizing preferences. Existing approaches rely on singular item-selection methods, limiting flexibility and user control. To address this challenge, we present Ranking Companion, a visual analytics approach for item-based ranking that combines model-driven active learning with human-driven item-selection methods. By drawing from six complementary item-selection methods, users can externalize listwise preferences based on selected candidate items, while an iterative machine learning process with a ranking model calculates ranking results, presented to users alongside explanations for interpretation. We evaluated Ranking Companion in a formative user study with 10 participants, in which participants used each item-selection method across three iterations, revealing tradeoffs in perceived ranking quality across accuracy, diversity, novelty, transparency, control, and satisfaction. Ranking Companion contributes a unified interactive item selection space and provides preliminary empirical guidance toward the hybrid use of multiple complementary item-selection methods in personalized item-based ranking creation.