文献详情
BPF plus plus : A Unified Factorization model for predicting retweet behaviors
文献类型：期刊
通讯作者：Li, CP (reprint author), Renmin Univ China, Key Lab Data Engn & Knowledge Engn MOE, Beijing, Peoples R China.
期刊名称：INFORMATION SCIENCES影响因子和分区
年：2020
卷：515
页码：218-232
ISSN：0020-0255
关键词：Collaborative filtering; Bayesian Poisson factorization; Probabilistic model; Retweet behaviors; Social network
所属部门：数据工程与知识工程教育部重点实验室
摘要：Recently, the prediction of retweet behaviors has attracted significant attention, as it can facilitate with a number of tasks, such as popular tweet prediction, personalized recommendation and business intelligence. However, in existing studies, two main problems exists in the prediction of retweet behaviors. (1) The relationship between users is extremely simple when social influences are used for prediction. (2) An effective framework that unifies the effects of both heterogeneous social rela ...More
Recently, the prediction of retweet behaviors has attracted significant attention, as it can facilitate with a number of tasks, such as popular tweet prediction, personalized recommendation and business intelligence. However, in existing studies, two main problems exists in the prediction of retweet behaviors. (1) The relationship between users is extremely simple when social influences are used for prediction. (2) An effective framework that unifies the effects of both heterogeneous social relations of users and multidimensional similarities of tweets does not exist. Therefore, we propose a unified factorization model that incorporates social influence and tweet similarity into a traditional Bayesian Poisson factorization (BPF) model, named BPF++. Specifically, we utilize a variety of social influence and tweet similarity jointly to improve performance. Furthermore, we integrate trust strengths between users and degrees of similarity between tweets to the framework. We adopt an efficient coordinate ascent algorithm to learn the parameters of the BPF++ model. Extensive experiments are conducted to evaluate the performance of our model on the Sina Weibo dataset. Results demonstrate improvements of 113.64% and 116.28% in the NDCG@3 and precision@3 scores, respectively, compared with BPF. (C) 2019 Elsevier Inc. All rights reserved. ...Hide

DOI：10.1016/j.ins.2019.12.017
百度学术：BPF plus plus : A Unified Factorization model for predicting retweet behaviors
语言：外文
基金：National Key Research Develop Plan [2018YFB1004401]; NSFCNational Natural Science Foundation of China [61772537, 61772536, 61702522, 61532021, 61902222]
作者其他论文



Fuzzy Rough Incremental Attribute Reduction Applying Dependency Measures.Liu, Yangming, Zhao, Suyun, Chen, Hong, et al. .WEB AND BIG DATA, APWEB-WAIM 2017, PT I. 2017, 10366, 484-492.
SET: Secure and Efficient Top-k Query in Two-Tiered Wireless Sensor Networks.Zhang, Xiaoying, Peng, Hui, Dong, Lei, et al. .WEB AND BIG DATA, APWEB-WAIM 2017, PT I. 2017, 10366, 495-510.
Survey of Foreign Passengers' Satisfaction of the Service Quality of Railway Passenger Transport.Yang, Nan, Zheng, Kai, Liu, Chang,.2018 2ND INTERNATIONAL CONFERENCE ON ADVANCES IN MANAGEMENT SCIENCE AND ENGINEERING (AMSE 2018). 2018, 292, 159-162.
Parallel Trajectory-to-Location Join.Shang, Shuo, Chen, Lisi, Zheng, Kai, et al. .IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING. 2019, 31(6), 1194-1207.
Event-based k-nearest neighbors query processing over distributed sensory data using fuzzy sets.Li, Yinglong, Chen, Hong, Lv, Mingqi, et al. .SOFT COMPUTING. 2019, 23(2), 483-495.