Abstract
Social tagging becomes more significant when the use of these tags can benefit the searching and browsing capabilities. In the recommendation systems, the use of information such as tags can improve the accuracy of the traditional recommendation by considering social
interests and social trusts between users. However, sparsity is one of the major problems in tag-based recommendation system because users do not always want to volunteer to contribute tags because it not compulsory. Therefore, this research proposes a neural network
tag-based recommendation that makes used of available tags to further support relationships with properties of items and users. The evaluation experiments show that the proposed approach improves the recommendation quality.
Metadata
Item Type: | Article |
---|---|
Creators: | Creators Email / ID Num. Khairudin, Nurkhairizan nurkhairizan@gmail.com Mohd Sharef, Nurfadhlina UNSPECIFIED Masrom, Suraya UNSPECIFIED Mustapha, Norwati UNSPECIFIED Mohd Noah, Shahrul Azman UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Neural networks (Computer science) Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Algorithms |
Divisions: | Universiti Teknologi MARA, Perak > Tapah Campus > Faculty of Computer and Mathematical Sciences |
Journal or Publication Title: | Multidisciplinary Informatics Journal |
UiTM Journal Collections: | Others > Multidisciplinary Informatics Journal - DISCONTINUE |
ISSN: | 2637-0042 |
Volume: | 1 |
Number: | 2 |
Page Range: | pp. 105-110 |
Keywords: | Data Sparsity; Social Tagging; Neural Network; Recommender Systems |
Date: | December 2018 |
URI: | https://ir.uitm.edu.my/id/eprint/39747 |