News Recommendation Systems-Accomplishments, Challenges Future Directions

Chong Feng*, Muzammil Khan, Arif Ur Rahman, Arshad Ahmad

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

54 Citations (Scopus)

Abstract

News publishers have decreased disseminating news through conventional newspapers and have migrated to the use of digital means like websites and purpose-built mobile applications. It is observed that news recommendation systems can automatically process lengthy articles and identify similar articles for readers considering predefined criteria. The objectives of the current work are to identify and classify the challenges in news recommendation domain, to identify state-of-the-art approaches and classify on the application domain, to identify datasets used for evaluation and their sources, the evaluation approaches used and to highlight the challenges explicitly addressed. The literature is thoroughly studied over the time span of 2001-2019 and shortlisted 81 related studies, broadly classified into six categories and discussed. The analysis showed that 60% of news recommendation system adopted a hybrid approach, 66% studies little talk about datasets, and addresses a few challenges from a long list of challenges in the news domain. This article is the first in the field to draw a comprehensive big picture of news recommendation and explore different dimensions covered in the studies. The last section presents the future research opportunities that lead to improving the recommendation of news articles in the news domain.

Original languageEnglish
Article number8963698
Pages (from-to)16702-16725
Number of pages24
JournalIEEE Access
Volume8
DOIs
Publication statusPublished - 2020

Keywords

  • Recommendations
  • literature review
  • news recommendation overview
  • news recommendations
  • recommendation techniques

Fingerprint

Dive into the research topics of 'News Recommendation Systems-Accomplishments, Challenges Future Directions'. Together they form a unique fingerprint.

Cite this