{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T14:43:58Z","timestamp":1777905838145,"version":"3.51.4"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Horizon Europe\u2019s European Innovation Council","award":["101071147"],"award-info":[{"award-number":["101071147"]}]},{"name":"Ag\u00e8ncia de Gesti\u00f3 d\u2019Ajuts Universitaris i de Recerca (AGAUR), Generalitat de Catalunya","award":["2023 DI 00080"],"award-info":[{"award-number":["2023 DI 00080"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:p>Eye-Tracking (ET) has recently gained popularity in Recommender Systems (RS) as a source of implicit feedback, effectively linking user attention to product saliency. However, leveraging user visual behaviour for recommendations does not scale due to the large volumes of ET data required to train RS models and the need for specialized equipment. This work investigates the extent to which state-of-the-art ET generative models can effectively mimic user information foraging behaviour in query-driven, search-recommendation tasks, as well as augment organic datasets with synthetic data for use in ET-based RS. We benchmark saliency and scan-path generators under task context, evaluating aggregate and individual saliency metrics and testing whether synthetic ET preserves category-sensitive gaze differences observed in humans. Our findings demonstrate that synthetic ET reproduces aggregate attention but fails to capture the search dynamics observed in organic data. Individual-level predictive accuracy remains low, with moderate improvements from fine-tuning and leave-one-out training, indicating data limitations.<\/jats:p>","DOI":"10.1145\/3803541","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:32:52Z","timestamp":1777638772000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Organic vs. Synthetic Attention: Evaluating the Utility of Eye Tracking Augmentation in Recommender Systems"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8423-357X","authenticated-orcid":false,"given":"Georgios","family":"Koutroumpas","sequence":"first","affiliation":[{"name":"Telef\u00f3nica Scientific Research","place":["Barcelona, Spain"]},{"name":"Universitat Polit\u00e8cnica de Catalunya","place":["Barcelona, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0810-4336","authenticated-orcid":false,"given":"Mireia","family":"Masias Bruns","sequence":"additional","affiliation":[{"name":"Telef\u00f3nica Scientific Research","place":["Barcelona, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8158-1673","authenticated-orcid":false,"given":"Sebastian","family":"Idesis","sequence":"additional","affiliation":[{"name":"Telef\u00f3nica Scientific Research","place":["Barcelona, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3013-3055","authenticated-orcid":false,"given":"Matteo","family":"Mazzini","sequence":"additional","affiliation":[{"name":"Mathematics","place":["Padova, Italy"]},{"name":"University of Padua","place":["Padova, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow","place":["Glasgow, United Kingdom"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0941-0260","authenticated-orcid":false,"given":"Sergi","family":"Abadal","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya","place":["Barcelona, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4212-0890","authenticated-orcid":false,"given":"Ioannis","family":"Arapakis","sequence":"additional","affiliation":[{"name":"Telef\u00f3nica Scientific Research","place":["Barcelona, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"e_1_3_3_2_1","unstructured":"Fakhri Abbas and Xi Niu. 2019. One Size Does Not Fit All: Modeling Users\u2019 Personal Curiosity in Recommender Systems. arXiv:arXiv:1907.00119"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s25092692"},{"key":"e_1_3_3_4_1","volume-title":"ECCV Workshop on Egocentric Perception, Interaction and Computing (EPIC)","author":"Assens Marc","year":"2018","unstructured":"Marc Assens, Xavier Giro-i Nieto, Kevin McGuinness, and Noel\u00a0E. O\u2019Connor. 2018. PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks. In ECCV Workshop on Egocentric Perception, Interaction and Computing (EPIC)."},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14146042"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2004.03.016"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_3_8_1","unstructured":"Giuseppe Cartella Vittorio Cuculo Alessandro D\u2019Amelio Marcella Cornia Giuseppe Boccignone and Rita Cucchiara. 2025. Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction. arxiv:https:\/\/arXiv.org\/abs\/2507.23021\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2507.23021"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-87715-9"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.42.3.692"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588015.3589511"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200474"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-97879-z"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00163"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00213"},{"key":"e_1_3_3_16_1","unstructured":"Yue Jiang Zixin Guo Hamed\u00a0Rezazadegan Tavakoli Luis\u00a0A. Leiva and Antti Oulasvirta. 2024. EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2404.10163\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2404.10163"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581096"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2019.102376"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"e_1_3_3_20_1","first-page":"107836","article-title":"May I have your Attention, please? An eye tracking study on emotional social media comments","volume":"146","author":"Kohout Susann","year":"2023","unstructured":"Susann Kohout, Sanne Kruikemeier, and Bert\u00a0N. Bakker. 2023. May I have your Attention, please? An eye tracking study on emotional social media comments. Computers in Human Behavior 146 (2023), 107836.","journal-title":"Computers in Human Behavior"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3759304"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888383"},{"key":"e_1_3_3_24_1","unstructured":"Peizhao Li Junfeng He Gang Li Rachit Bhargava Shaolei Shen Nachiappan Valliappan Youwei Liang Hongxiang Gu Venky Ramachandran Golnaz Farhadi Yang Li Kai\u00a0J Kohlhoff and Vidhya Navalpakkam. 2024. UniAR: A Unified model for predicting human Attention and Responses on visual content. arxiv:https:\/\/arXiv.org\/abs\/2312.10175\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2312.10175"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.796895"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715669.3725882"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"e_1_3_3_28_1","volume-title":"Workshop on Reasoning and Planning for Large Language Models","author":"Lvov Dmitry","year":"2025","unstructured":"Dmitry Lvov and Ilya Pershin. 2025. LogitGaze: Predicting Human Attention Using Semantic Information from Vision-Language Models. In Workshop on Reasoning and Planning for Large Language Models. https:\/\/openreview.net\/forum?id=Om4j6IVb42"},{"key":"e_1_3_3_29_1","unstructured":"Xin Ma Mingyue Li and Xuguang Liu. 2024. Advancements in Recommender Systems: A Comprehensive Analysis Based on Data Algorithms and Evaluation. arXiv:arXiv:2407.18937"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781315642956"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649902.3653471"},{"key":"e_1_3_3_32_1","unstructured":"Sounak Mondal Zhibo Yang Seoyoung Ahn Dimitris Samaras Gregory Zelinsky and Minh Hoai. 2023. Gazeformer: Scalable Effective and Fast Prediction of Goal-Directed Human Attention. arxiv:https:\/\/arXiv.org\/abs\/2303.15274\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2303.15274"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hfh.2022.100031"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-018-01193-y"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.03.019"},{"key":"e_1_3_3_38_1","unstructured":"Shaina Raza Mizanur Rahman Safiullah Kamawal Armin Toroghi Ananya Raval Farshad Navah and Amirmohammad Kazemeini. 2024. A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice. arXiv:arXiv:2407.13699"},{"key":"e_1_3_3_39_1","unstructured":"Chandan\u00a0K. Reddy Llu\u00eds M\u00e0rquez Fran Valero Nikhil Rao Hugo Zaragoza Sambaran Bandyopadhyay Arnab Biswas Anlu Xing and Karthik Subbian. 2022. Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. (2022). arxiv:https:\/\/arXiv.org\/abs\/2206.06588"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715669.3723113"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/52.3-4.591"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2021.3066072"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbr.2025.100723"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/info11060300"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.2307\/2331554"},{"key":"e_1_3_3_46_1","unstructured":"Yinan Sun Xiongkuo Min Huiyu Duan and Guangtao Zhai. 2024. How is Visual Attention Influenced by Text Guidance? Database and Model. arxiv:https:\/\/arXiv.org\/abs\/2404.07537\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2404.07537"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00130487"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.2307\/3001913"},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10100-019-00628-x"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642942"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2024.1309047"},{"key":"e_1_3_3_54_1","article-title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","volume":"2005","author":"Yang Zhibo","year":"2020","unstructured":"Zhibo Yang, Lihan Huang, Yupei Chen, Zijun Wei, Seoyoung Ahn, Gregory\u00a0J. Zelinsky, Dimitris Samaras, and Minh Hoai. 2020. Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning. CoRR abs\/2005.14310 (2020). arXiv:https:\/\/arXiv.org\/abs\/2005.14310https:\/\/arxiv.org\/abs\/2005.14310","journal-title":"CoRR"},{"key":"e_1_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00166"},{"key":"e_1_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11512"},{"key":"e_1_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.63317\/257i69rmz36p"},{"key":"e_1_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000066"},{"key":"e_1_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959150"},{"key":"e_1_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3167132.3167291"}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T13:02:40Z","timestamp":1777640560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,1]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,1]]}},"alternative-id":["10.1145\/3803541"],"URL":"https:\/\/doi.org\/10.1145\/3803541","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,1]]},"assertion":[{"value":"2026-05-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}