Jingwei Kang
PhD candidate · Information Retrieval Lab (IRLab), University of Amsterdam
I study recommender systems in streaming media services, where recommendations are shown in carousel interfaces. My work focuses on user behaviour modelling and offline evaluation; I have also worked on learning to rank. I am a PhD candidate at the University of Amsterdam, supervised by prof. dr. Maarten de Rijke and dr. Harrie Oosterhuis.
Research
User behaviour modelling
- Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces SIGIR ’26
- Rethinking Click Models in Light of Carousel Interfaces: Theory-Based Categorization and Design of Click Models ICTIR ’25
- RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces SIGIR ’25
Offline evaluation
- Revisiting N2DCG: An Empirically Grounded Reformulation of Carousel Recommendation Evaluation CIKM ’26
Learning to rank
Publications
2026
-
Short paper
Revisiting N2DCG: An Empirically Grounded Reformulation of Carousel Recommendation Evaluation
Shows that N2DCG, the NDCG adaptation for carousels, uses an ideal ranking that violates carousel constraints and a discount that does not match observed browsing; proposes a reformulated metric grounded in eye-tracking data.
@inproceedings{10.1145/3799682.3839894, author = {Kang, Jingwei and de Leon-Martinez, Santiago and de Rijke, Maarten and Oosterhuis, Harrie}, title = {Revisiting N2DCG: An Empirically Grounded Reformulation of Carousel Recommendation Evaluation}, year = {2026}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3799682.3839894}, doi = {10.1145/3799682.3839894}, booktitle = {Proceedings of the 35th ACM International Conference on Information and Knowledge Management}, pages = {7284–7289}, numpages = {6}, location = {Rome, Italy}, series = {CIKM '26} } -
Doctoral symposium
From Click Modeling to Offline and Off-Policy Evaluation in Carousel Recommendation
Lays out the PhD programme: a click-model design framework built on relations between observed variables, discrete-choice click models, carousel-specific offline metrics, and off-policy evaluation of carousel recommendation policies from logged data.
@inproceedings{10.1145/3773078.3831937, author = {Kang, Jingwei}, title = {From Click Modeling to Offline and Off-Policy Evaluation in Carousel Recommendation}, year = {2026}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3773078.3831937}, doi = {10.1145/3773078.3831937}, booktitle = {Proceedings of the 20th ACM Conference on Recommender Systems}, pages = {1932–1938}, numpages = {7}, location = {Minneapolis, MN, USA}, series = {RecSys '26} } -
Full paper
Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces
Tests four web-search behavioural assumptions on carousel eye-tracking data: the F-pattern holds only vertically, users follow an L-shaped pattern after clicking, the examination hypothesis fails, and users skip carousel headings.
@inproceedings{10.1145/3805712.3809657, author = {Kang, Jingwei and de Rijke, Maarten and Oosterhuis, Harrie}, title = {Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces}, year = {2026}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3805712.3809657}, doi = {10.1145/3805712.3809657}, booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {734–744}, numpages = {11}, location = {Melbourne, Australia}, series = {SIGIR '26} }
2025
-
Resource paper
A Large-Scale Web Search Dataset for Federated Online Learning to Rank
A large-scale web search dataset built for studying federated online learning to rank.
@inproceedings{10.1145/3746252.3761651, author = {Gregoriadis, Marcel and Kang, Jingwei and Pouwelse, Johan}, title = {A Large-Scale Web Search Dataset for Federated Online Learning to Rank}, year = {2025}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3746252.3761651}, doi = {10.1145/3746252.3761651}, booktitle = {Proceedings of the 34th ACM International Conference on Information and Knowledge Management}, pages = {6387–6391}, numpages = {5}, location = {Seoul, Republic of Korea}, series = {CIKM '25} } -
Full paper · Best Paper Honorable Mention
Rethinking Click Models in Light of Carousel Interfaces: Theory-Based Categorization and Design of Click Models
Replaces outdated click-model taxonomies with three mathematically grounded design choices that cover single-list, grid and carousel click models (PGMs and neural), and derives a new carousel click model from them.
@inproceedings{10.1145/3731120.3744585, author = {Kang, Jingwei and de Rijke, Maarten and de Leon-Martinez, Santiago and Oosterhuis, Harrie}, title = {Rethinking Click Models in Light of Carousel Interfaces: Theory-Based Categorization and Design of Click Models}, year = {2025}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3731120.3744585}, doi = {10.1145/3731120.3744585}, booktitle = {Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)}, pages = {44–55}, numpages = {12}, location = {Padua, Italy}, series = {ICTIR '25} } -
Resource paper
RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces
The first public carousel dataset combining eye tracking, clicks and cursor movements (87 users, 3,477 interactions), revealing a golden-triangle, F-shaped browsing pattern.
@inproceedings{10.1145/3726302.3730301, author = {de Leon-Martinez, Santiago and Kang, Jingwei and Moro, Robert and de Rijke, Maarten and Kveton, Branislav and Oosterhuis, Harrie and Bielikova, Maria}, title = {RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces}, year = {2025}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3726302.3730301}, doi = {10.1145/3726302.3730301}, booktitle = {Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {3702–3711}, numpages = {10}, location = {Padua, Italy}, series = {SIGIR '25} }
2024
-
Short paper
Estimating the Hessian Matrix of Ranking Objectives for Stochastic Learning to Rank with Gradient Boosted Trees
Makes gradient-boosted decision trees usable for stochastic learning to rank by estimating the Hessian of ranking objectives.
@inproceedings{10.1145/3626772.3657918, author = {Kang, Jingwei and de Rijke, Maarten and Oosterhuis, Harrie}, title = {Estimating the Hessian Matrix of Ranking Objectives for Stochastic Learning to Rank with Gradient Boosted Trees}, year = {2024}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3626772.3657918}, doi = {10.1145/3626772.3657918}, booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {2390–2394}, numpages = {5}, location = {Washington DC, USA}, series = {SIGIR '24} }
Education
-
Ph.D. in Recommender Systems
University of Amsterdam, Amsterdam, the Netherlands, 2023–present
Dissertation topic: Full-page Personalization
-
M.Sc. in Data Science
Radboud University, Nijmegen, the Netherlands, 2021–2023
-
B.Sc. in Data Science
Central South University, Changsha, China, 2016–2020
Contact
Email is the best way to reach me, whether about a paper, a dataset or a possible collaboration.