Name
Abstract | ||
|---|---|---|
Users of e-commerce sites often read reviews of products before deciding to purchase them. Many commercial sites simply select the reviews with the highest quality, according to the votes they have received by users who read the reviews. However, recent work has shown that such a selection may contain redundant information. Therefore, while selecting top reviews, it has been proposed to also consider their coverage (i.e., how many product aspects are covered by them). The goal of this paper is to further improve the top reviews set, using personalization criteria. This is motivated by the fact that the importance of product aspects to different users may vary and users prefer to focus on the most important aspects to them. The objective of our work is to consider the personal preferences of users in review recommendation, by selecting a personalized top reviews set (PTRS), which includes reviews of which the content is related to the aspects important to the user. An experimental evaluation with two public review datasets demonstrates the effectiveness of our approach on computing PTRS that have high quality, coverage, and relevance to the aspects that are important for the user. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.neucom.2016.10.081 | Neurocomputing |
Keywords | Field | DocType |
Personalization,Review ranking,E-commerce,Collaborative filtering | World Wide Web,Collaborative filtering,Information retrieval,Computer science,E-commerce,Personalization | Journal |
Volume | ISSN | Citations |
254 | 0925-2312 | 1 |
PageRank | References | Authors |
0.36 | 21 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wenting Tu | 1 | 85 | 9.48 |
| David Wai-Lok Cheung | 2 | 2469 | 282.09 |
| Nikos Mamoulis | 3 | 4621 | 263.82 |