Towards Simulation-Based Evaluation of Recommender Systems with Carousel Interfaces

Author:

Rahdari Behnam1ORCID,Brusilovsky Peter1ORCID,Kveton Branislav2ORCID

Affiliation:

1. University of Pittsburgh, Pittsburgh, USA

2. Amazon, Seattle, USA

Abstract

Offline data-driven evaluation is considered a low-cost and more accessible alternative to the online empirical method of assessing the quality of recommender systems. Despite their popularity and effectiveness, most data-driven approaches are unsuitable for evaluating interactive recommender systems. In this article, we attempt to address this issue by simulating the user interactions with the system as a part of the evaluation process. Particularly, we demonstrate that simulated users find their desired item more efficiently when recommendations are presented as a list of carousels compared to a simple ranked list.

Publisher

Association for Computing Machinery (ACM)

Reference73 articles.

1. Eugene Agichtein, Eric Brill, Susan Dumais, and Robert Ragno. 2006. Learning user interaction models for predicting web search result preferences. In Proceedings of the 29th Annual International ACM SIGIR Conference. ACM, New York, NY, 3–10.

2. Carousel Personalization in Music Streaming Apps with Contextual Bandits

3. Svetlin Bostandjiev, John O’Donovan, and Tobias Höllerer. 2012. TasteWeights: A visual interactive hybrid recommender system. In Proceedings of the 6th ACM Conference on Recommender System. ACM, New York, NY, 35–42.

4. SIREN

5. The FindMe approach to assisted browsing;Burke Robin;IEEE Intelligent Systems,1997

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. CARE: An Infrastructure for Evaluation of Carousel-Based Recommender Interfaces;Companion Proceedings of the 29th International Conference on Intelligent User Interfaces;2024-03-18

2. Introduction to the Special Issue on Perspectives on Recommender Systems Evaluation;ACM Transactions on Recommender Systems;2024-03-07

3. User Simulation for Evaluating Information Access Systems;Foundations and Trends® in Information Retrieval;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3