Dynamic Connection-Based Social Group Recommendation

Group recommendation has become highly demanded when users communicate in the forms of group activities in online sharing communities. These group activities include student group study, family TV program watching, friends travel decision, etc. Existing group recommendation techniques mainly focus o...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on knowledge and data engineering Vol. 32; no. 3; pp. 453 - 467
Main Authors Qin, Dong, Zhou, Xiangmin, Chen, Lei, Huang, Guangyan, Zhang, Yanchun
Format Journal Article
LanguageEnglish
Published New York IEEE 01.03.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Australia
Collaboration
collaborative filtering
Data mining
Digital media
Group recommendation
Media
Motion pictures
Recommender systems
social connection
Social groups
social item
Subgroups
User groups
Online AccessGet full text

Cover

More Information
Summary:Group recommendation has become highly demanded when users communicate in the forms of group activities in online sharing communities. These group activities include student group study, family TV program watching, friends travel decision, etc. Existing group recommendation techniques mainly focus on the small user groups. However, online sharing communities have enabled group activities among thousands of users. Accordingly, recommendation over large groups has become urgent. In this paper, we propose a new framework to accomplish this goal by exploring the group interests and the connections between group users. We first divide a big group into different interest subgroups, each of which contains users closely connected with each other and sharing the similar interests. Then, for each interest subgroup, our framework exploits the connections between group users to collect a comparably compact potential candidate set of media-user pairs, on which the collaborative filtering is performed to generate an interest subgroup-based recommendation list. After that, a novel aggregation function is proposed to integrate the recommended media lists of all interest subgroups as the final group recommendation results. Extensive experiments have been conducted on two real social media datasets to demonstrate the effectiveness and efficiency of our proposed approach.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2018.2879658