Loading...

Designing an Efficient Algorithm for Group Recommender Systems based
on Group Profile

Morshedi Lahvas, Mojde | 2016

1550 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 48783 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Movaghar Rahimabadi, Ali
  7. Abstract:
  8. Recommender Systems have become an attractive field within the recent decade since they facilitate users’ selection process in limited time. Conventional recommender systems have proposed numerous methods with a focus on recommending to individual users. Recently, due to a significant increase in the number of users, studies in this field have shifted to properly identify groups of people with similar preferences and provide a list of recommendations for each group. Because, offering a recommendations list to each individual undergoes computational cost and sometimes is not possible. So far, most of the previous studies requires the restrictive assumptions such as: (1) limited number of users, (2) number of groups, (3) average number of group members, and (4) full knowledge of the network topological structure. To overcome these shortcomings, we propose two novel approaches to improve the accuracy of recommendations list by using the concept of network centrality and cognitive science. Our approach is evaluated in different types of social group recommender systems in comparison with several common strategies over real-world datasets. Experimental results demonstrate that the group formation and group profiling based on both concepts leads to the more accurate recommendations list for each group
  9. Keywords:
  10. Cognitive Science ; Social Networks ; Group Recammender Systems ; Group Profile ; Network Centrality

 Digital Object List

 Bookmark

...see more