Enhancing Quality of Movies Recommendation Through Contextual Ontological User Profiling

Citation

Khan, Mohammad Wahiduzzaman and Chan, Gaik Yee and Chua, Fang Fang (2019) Enhancing Quality of Movies Recommendation Through Contextual Ontological User Profiling. In: Data Mining and Big Data. Springer, Communications in Computer and Information Science, pp. 307-319. ISBN 978-981-32-9562-9

[img] Text
272.pdf - Published Version
Restricted to Repository staff only

Download (595kB)

Abstract

Nowadays, the Internet and Cloud Computing technologies have enabled movies watching to be enjoyed anytime and anywhere in richer varieties and choices. As a result, one will be overwhelmed and tend to make poor choices. The increasing on-demand movies services motivates more choices of the programs to be offered and users need recommendation system to provide them with contextual and personalized suggestions. This paper proposes to use contextual ontological user profiling for movies recommendation which considers personalization in enhancing the effectiveness of the recommendations. We evaluated the performance of our proposed solution with few scenarios representing problems aroused from traditional collaborative and content-based recommendations. These problems are the cold start, data sparsity, over specialization, gray sheep and inefficiency issue. Evaluation results and analysis show that proposed work not only is capable of resolving these problems but is also competent in mitigating the scalability and inefficiency issue.

Item Type: Book Section
Uncontrolled Keywords: Cloud Computing, Collaborative filtering, Content-based, Contextual, Ontology, User profiling
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 17 Sep 2021 03:32
Last Modified: 17 Sep 2021 03:32
URII: http://shdl.mmu.edu.my/id/eprint/8986

Downloads

Downloads per month over past year

View ItemEdit (login required)