HGGC: A hybrid group recommendation model considering group cohesion

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 44
  • Download : 0
In the real world, people organize and participate in many group activities. Group recommendation that finds out preferable items for a group of users is a challenging problem since it is difficult to properly aggregate diverse preferences among the members. Group cohesion denotes proportion of group members who actively participate in various activities relevant to group's objectives. In a strongly cohesive group, most members actively participate in group decision, while many of group members in a weakly cohesive group are bystanders who just follow the other member's decision. Since group cohesion is an important factor in group recommendation, the concept of group cohesion needs to be properly reflected to the recommendation model. We present a new approach about group recommendation that appropriately captures group cohesion. A hybrid model that considers content information and rating data simultaneously is also proposed to alleviate a well-known data sparsity problem in group recommendation. We use a heterogeneous information network (HIN) that can contain rich information about entities and relationships from which additional content information can be extracted. Then, this information is properly incorporated to the group recommendation model. Experimental results on the real datasets show that our proposed method outperforms the existing state-of-the-art methods and improves recommendation performances significantly. (C) 2019 Elsevier Ltd. All rights reserved.
Publisher
PERGAMON-ELSEVIER SCIENCE LTD
Issue Date
2019-12
Language
English
Article Type
Article
Citation

EXPERT SYSTEMS WITH APPLICATIONS, v.136, pp.73 - 82

ISSN
0957-4174
DOI
10.1016/j.eswa.2019.05.054
URI
http://hdl.handle.net/10203/267698
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0