Joint Modeling of Candidate and Recruiter Preferences for Fair Two-Sided Job Matching

Conference Paper (2026)
Author(s)

Clara Rus (Universiteit van Amsterdam)

Masoud Mansoury (TU Delft - Multimedia Computing)

Andrew Yates (Johns Hopkins University)

Maarten de Rijke (Universiteit van Amsterdam)

Research Group
Multimedia Computing
DOI related publication
https://doi.org/10.1007/978-3-032-21324-2_27 Final published version
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Multimedia Computing
Pages (from-to)
335-351
Publisher
Springer
ISBN (print)
9783032213235
Event
48th European Conference on Information Retrieval, ECIR 2026 (2026-03-29 - 2026-04-02), Delft, Netherlands
Downloads counter
11
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Recommender systems in recruitment platforms involve two active sides, candidates and recruiters, each with distinct goals and preferences. Most recommendation methods address only one side of the problem, leading to potentially ineffective matches. We propose a two-sided fusion framework that jointly models candidate and recruiter preferences to enhance mutual matches between candidates and recruiters. We also propose a personalized two-sided fusion approach to enhance the fairness of job recommendations. Experiments on the XING recruitment dataset show that the proposed approach improves fairness and compatibility, demonstrating the benefits of incorporating two-sided preferences in fairness-aware recommendations.

Files

978-3-032-21324-2_27.pdf
(pdf | 1.33 Mb)
Taverne
warning

File under embargo until 24-09-2026