期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 170, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2020.114537
关键词
Tourism recommender system; Multi-criteria recommendation; Cultural difference; User preference modeling; Multi-dimensional model; Tensor factorization
类别
资金
- National Research Foundation of Korea (NRF) - Korea government (MSIP) [NRF-2017R1A2B4010774, NRF-2018K1A3A1A09078981]
This paper proposes two "single tensor" models to consider the inherent structure and interrelations of users, items, multi-criteria ratings, and cultural groups in recommendation processes. Experimental results show that the proposed models outperform other techniques in terms of MAE, with improvements of 21.31% and 7.11%. Multiple-criteria ratings and cultural group factors have positive influences on recommendation performances.
Many tourism recommender systems have been studied to offer users the items meeting their interests. However, it is a non-trivial task to reflect the multi-criteria ratings and the cultural differences, which significantly influence users? reviews of tourism facilities, into recommendation services. This paper proposes two ?single tensor? models, consisting of users (or countries), items, multi-criteria ratings, and cultural groups, in order to consider simultaneously an inherent structure and interrelations of these factors into recommendation processes. With one Tripadvisor dataset, including 13 K users from 120 countries, experiments demonstrated that, in terms of MAE, the two proposed models for user and country give an improvement of 21.31% and 7.11% than other collaborative filtering and multi-criteria recommendation techniques. Besides, there were the positive influences of multiple-criteria ratings and cultural group factors on recommendation performances. The comparative analysis of several variants of the proposed models showed that considering Western and Eastern cultures is appropriate for improving predictive performances and their stability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据