X
Xiaolin Zheng
Researcher at Zhejiang University
Publications - 90
Citations - 1829
Xiaolin Zheng is an academic researcher from Zhejiang University. The author has contributed to research in topics: Recommender system & Collaborative filtering. The author has an hindex of 22, co-authored 88 publications receiving 1307 citations. Previous affiliations of Xiaolin Zheng include Stanford University & Association for Computing Machinery.
Papers
More filters
Journal ArticleDOI
Capturing the essence of word-of-mouth for social commerce: Assessing the quality of online e-commerce reviews by a semi-supervised approach
TL;DR: A semi-supervised system that exploits two opportunities: the improvement of classification performance through the use of a few labeled instances and numerous unlabeled instances, and the effectiveness of the social characteristics of e-commerce communities as identifiers of influential reviewers who write high-quality reviews.
Journal ArticleDOI
An efficient and reliable approach for quality-of-service-aware service composition
TL;DR: This paper proposes a novel heuristic algorithm for an efficient and reliable selection of trustworthy services in a service composition and demonstrates that the approach obtains a close-to-optimal and reliable solution within a reasonable computation time.
Proceedings Article
Context- ware collaborative topic regression with social matrix factorization for recommender systems
TL;DR: A novel context-aware hierarchical Bayesian method that can make predictions for each user-item subgroup, which incorporate not only topic modeling to mine item content but also social matrix factorization to handle ratings and social relationships.
Journal ArticleDOI
A hybrid approach for movie recommendation via tags and ratings
TL;DR: Experimental results show that the proposed hybrid recommendation approach using tags and ratings significantly outperforms three categories of recommendation approaches, namely, user-based collaborative filtering (CF), model-based CF, and topic model based CF.
Proceedings ArticleDOI
DTCDR: A Framework for Dual-Target Cross-Domain Recommendation
TL;DR: In this paper, a new framework, DTCDR, for Dual-Target Cross-Domain Recommendation is proposed, based on Multi-Task Learning (MTL), which can significantly improve the recommendation accuracies on both richer and sparser domains and outperform the state-of-the-art single-domain and cross-domain approaches.