HYPNER: a hybrid approach for personalised news recommendation

Citation

Darvishy, Asghar and Ibrahim, Hamidah and Sidi, Fatimah and Mustapha, Aida (2020) HYPNER: a hybrid approach for personalised news recommendation. IEEE Access, 8. 46877 - 46894. ISSN 2169-3536

Abstract

A personalised news recommendation system extracts news set from multiple press releases and presents the recommended news to the user. In an effort to build a better recommender system with high accuracy, this paper proposes a personalised news recommendation framework named Hybrid Personalised NEws Recommendation (HYPNER). HYPNER combines both collaborative filtering-based and content-based filtering methods. The proposed framework aims at improving the accuracy of news recommendation by resolving the issues of scalability due to large news corpus, enriching the user's profile, representing the exact properties and characteristics of news items, and recommending diverse set of news items. Validation experiments showed that HYPNER achieved 81.56% improvement in F1 -score and 5.33% in diversity as compared to an existing recommender system, SCENE.

Download File

Text (Abstract)
NEWS.pdf
Download (28kB)

Official URL or Download Paper: https://ieeexplore.ieee.org/document/9026823

Additional Metadata

Item Type:	Article
Divisions:	Faculty of Computer Science and Information Technology
DOI Number:	https://doi.org/10.1109/ACCESS.2020.2978505
Publisher:	Institute of Electrical and Electronics Engineers
Keywords:	Collaborative filtering; Content-based filtering; News recommendation; Personalised news recommendation
Depositing User:	Ms. Nuraida Ibrahim
Date Deposited:	20 Sep 2021 23:31
Last Modified:	20 Sep 2021 23:31
Altmetrics:	http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/ACCESS.2020.2978505
URI:	http://psasir.upm.edu.my/id/eprint/89241
Statistic Details:	View Download Statistic

Actions (login required)

View Item