Title :
Comparison of group recommendation techniques in social networks
Author :
Minaei-Bidgoli, B. ; Esmaeili, Leila ; Nasiri, Mahdi
Author_Institution :
Comput. Eng. Dept., Iran Univ. of Sci. & Technol., Tehran, Iran
Abstract :
Virtual communities and groups are known as one of the features of social networks for creating the possibility for users to join together and interact. Regarding the growth of social networks as well as attracting new users of various ages and creation of different groups, assisting users seems quite necessary. Along with studying some of the common recommender methods in social networks in this paper, a new method is explained. This new method is designed using d-tree classification, association rules and the concepts of information theory which compared with others, it gives better results. It is also possible in this system to offer recommendations to new users who have just joined the network and do not have any links.
Keywords :
collaborative filtering; data mining; information theory; pattern classification; recommender systems; social networking (online); trees (mathematics); association rules; collaborative filtering; d-tree classification; group recommendation techniques; information theory; social networks; user interaction; virtual communities; virtual groups; Association rules; Noise; Recommender systems; Social network services; Tin; collaborative filtering; content based filtering; hybrid; recommender system; social network;
Conference_Titel :
Computer and Knowledge Engineering (ICCKE), 2011 1st International eConference on
Conference_Location :
Mashhad
Print_ISBN :
978-1-4673-5712-8
DOI :
10.1109/ICCKE.2011.6413357
