Neural Serendipity Recommendation: Exploring the Balance between Accuracy and Novelty with Sparse Explicit Feedback

doi:10.1145/3396607

	Neural Serendipity Recommendation: Exploring the Balance between Accuracy and Novelty with Sparse Explicit Feedback
	Xu, Yuanbo 1; Yang, Yongjian 1; Wang, En 1; Han, Jiayu 1; Zhuang, Fuzhen 2,3,6,7; Yu, Zhiwen 4; Xiong, Hui 5
刊名	ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
	2020-07-01
卷号	14 期号:4 页码:25
关键词	Serendipity recommender system muti-layer percetron matrix factorization
ISSN号	1556-4681
DOI	10.1145/3396607
英文摘要	Recommender systems have been playing an important role in providing personalized information to users. However, there is always a trade-off between accuracy and novelty in recommender systems. Usually, many users are suffering from redundant or inaccurate recommendation results. To this end, in this article, we put efforts into exploring the hidden knowledge of observed ratings to alleviate this recommendation dilemma. Specifically, we utilize some basic concepts to define a concept, Serendipity, which is characterized by highsatisfaction and low-initial-interest. Based on this concept, we propose a two-phase recommendation problem which aims to strike a balance between accuracy and novelty achieved by serendipity prediction and personalized recommendation. Along this line, a Neural Serendipity Recommendation (NSR) method is first developed by combining Muti-Layer Percetron and Matrix Factorization for serendipity prediction. Then, a weighted candidate filtering method is designed for personalized recommendation. Finally, extensive experiments on real-world data demonstrate that NSR can achieve a superior serendipity by a 12% improvement in average while maintaining stable accuracy compared with state-of-the-art methods.
资助项目	National Natural Science Foundations of China[61772230] ; National Natural Science Foundations of China[61972450] ; National Natural Science Foundations of China[61773361] ; Natural Science Foundation of China for Young Scholars[61702215] ; China Postdoctoral Science Foundation[2017M611322] ; China Postdoctoral Science Foundation[2018T110247] ; China Postdoctoral Science Foundation[BX20190140] ; Changchun Science and Technology Development Project[18DY005]
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000583626600013
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16013]
专题	中国科学院计算技术研究所
通讯作者	Wang, En
作者单位	1.Jilin Univ, Qianjin St 2699, Changchun 130012, Jilin, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Beijing Adv Innovat Ctr Imaging Theory & Technol, Beijing, Peoples R China 4.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shanxi, Peoples R China 5.Rutgers State Univ, Sch Business, Newark, NY USA 6.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 7.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Theory & Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Xu, Yuanbo,Yang, Yongjian,Wang, En,et al. Neural Serendipity Recommendation: Exploring the Balance between Accuracy and Novelty with Sparse Explicit Feedback[J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,2020,14(4):25.
APA	Xu, Yuanbo.,Yang, Yongjian.,Wang, En.,Han, Jiayu.,Zhuang, Fuzhen.,...&Xiong, Hui.(2020).Neural Serendipity Recommendation: Exploring the Balance between Accuracy and Novelty with Sparse Explicit Feedback.ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,14(4),25.
MLA	Xu, Yuanbo,et al."Neural Serendipity Recommendation: Exploring the Balance between Accuracy and Novelty with Sparse Explicit Feedback".ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 14.4(2020):25.