An Efficient Algorithm for Group Recommender Systems based on Centrality of Users<br/>

Please enable javascript in your browser.

An Efficient Algorithm for Group Recommender Systems based on Centrality of Users

322 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53239 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Movaghar, Ali
Abstract:
The significant increase in data volume makes it difficult to choose from a variety of options. Recommender systems help people choose their priorities in a limited time and facilitate the selection process for users. These systems predict users 'interest in the future by examining users' information and their preferences. Recently, with the significant increase in the number of users, studies in this field have changed so that groups of people with similar priorities are correctly identified and a list of recommendations is provided for each group. Identifying groups and presenting a suggestion list each require high computational cost and are often inefficient. The centrality of nodes will be effective in identifying and proposing groups, which has not been well addressed in past research. The project focuses on grouping users, taking into account the centrality of the nodes, giving each group a list of suggestions based on the priorities of its members
Keywords:
Recommender System ; Grouping ; User Centered Design ; Group Recammender Systems ; Nodes Centrality