Work

Learning to Rank with Variable Result Presentation Lengths

Year: 2025

Type: conference-paper

Abstract: Learning to Rank (LTR) methods generally assume that each document in a top-K ranking is presented in an equal format. However, previous work has shown that users' perceptions of relevance can be changed by varying presentations, i.e., allocating more vertical space to some documents to provide additional textual or image information. Furthermore, presentation length can also redirect attention, as users are more likely to notice longer presentations when scrolling through results. Deciding on the document presentation lengths in a fixed vertical space ranking is an important problem that has not been addressed by existing LTR methods.

Source: International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

DOI: 10.1145/3726302.3730020

Authors: Norman Knyazev, Harrie Oosterhuis

Institution: Radboud University Nijmegen

Language: English

Topic: Information Retrieval and Search Behavior

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Nederlandse Organisatie voor Wetenschappelijk Onderzoek, Universitas Brawijaya

Awards: G2001686281, Search Systems with a Bayesian Understanding of Their Users (BAYES-SEARCH)