Publication Details

RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces

DE Leon Martinez Santiago Jose, KANG Jingwei, MORO Robert, DE Rijke Maarten, KVETON Branislav, OOOSTERHUIS Harrie and BIELIKOVÁ Mária. RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces. In: SIGIR '25: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: Association for Computing Machinery, 2025, pp. 3702-3711. ISBN 979-8-4007-1592-1. Available from: https://dl.acm.org/doi/abs/10.1145/3726302.3730301
Czech title
RecGaze: První datová sada pro sledování očí a interakci uživatele pro karuselová rozhraní
Type
conference paper
Language
english
Authors
de Leon Martinez Santiago Jose (DCGM FIT BUT)
Kang Jingwei (UVA)
Moro Robert (KInIT)
De Rijke Maarten (UVA)
Kveton Branislav (KInIT)
Ooosterhuis Harrie (UVA)
Bieliková Mária, prof. Ing., PhD. (DCGM FIT BUT)
URL
Keywords

Carousel interfaces, Browsing behavior, Eye tracking

Abstract

Carousel interfaces are widely used in e-commerce and streaming services, but little research has been devoted to them. Previous studies of interfaces for presenting search and recommendation results have focused on single ranked lists, but it appears their results cannot be extrapolated to carousels due to the added complexity. Eye tracking is a highly informative approach to understanding how users click, yet there are no eye tracking studies concerning carousels. There are very few interaction datasets on recommenders with carousel interfaces and none that contain gaze data. We introduce the RecGaze dataset: the first comprehensive feedback dataset on carousels that includes eye tracking results, clicks, cursor movements, and selection explanations. The dataset comprises of interactions from 3  movie selection tasks with 40 different carousel interfaces per user. In total, 87 users and 3,477 interactions are logged. In addition to the dataset, its description and possible use cases, we provide results of a survey on carousel design and the first analysis of gaze data on carousels, which reveals a golden triangle or F-pattern browsing behavior. Our work seeks to advance the field of carousel interfaces by providing the first dataset with eye tracking results on carousels.In this manner, we provide and encourage an empirical understanding of interactions with carousel interfaces, for building better gaze-based recommendation systems.

Published
2025
Pages
3702-3711
Proceedings
SIGIR '25: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval
Conference
The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padova, IT
ISBN
979-8-4007-1592-1
Publisher
Association for Computing Machinery
Place
New York, US
DOI
10.1145/3726302.3730301
BibTeX 
@INPROCEEDINGS{FITPUB13459,
   author = "Jose Santiago Martinez Leon de and Jingwei Kang and Robert Moro and Maarten Rijke De and Branislav Kveton and Harrie Ooosterhuis and M\'{a}ria Bielikov\'{a}",
   title = "RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces",
   pages = "3702--3711",
   booktitle = "SIGIR '25: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval",
   year = 2025,
   location = "New York, US",
   publisher = "Association for Computing Machinery",
   ISBN = "979-8-4007-1592-1",
   doi = "10.1145/3726302.3730301",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13459"
}
Back to top