News Recommendation Method Based on Topic Extraction and User Interest Transfer

Yimeng Wei (), Guiying Wei () and Sen Wu ()
Additional contact information
Yimeng Wei: University of Science and Technology Beijing
Guiying Wei: University of Science and Technology Beijing
Sen Wu: University of Science and Technology Beijing

A chapter in LISS 2021, 2022, pp 208-219 from Springer

Abstract: Abstract Contemporary news reader faces the problem of information explosion which has led to the difficulty for users to acquire information they really need. News recommendation system plays a significant role in screening interested news for users, but traditional news recommendation methods often face cold-start problem and are difficult to reflect the user personalized differences. This paper proposes a news recommendation method based on topic extraction and user interest transfer (NRTU). The proposed model extracts news topic tags by analyzing semantic information from texts which alleviates cold-start problem of news and applies Long-Short Term Memory (LSTM) model to represent user interest transfer. Extensive experiments on a real-world dataset validate the effectiveness of our approach.

Keywords: News recommendation; User sequential interest; Topic extraction (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-16-8656-6_20

Ordering information: This item can be ordered from
http://www.springer.com/9789811686566

DOI: 10.1007/978-981-16-8656-6_20

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().