UTSP: User-Based Two-Step Recommendation with Popularity Normalization towards Diversity and Novelty

13Citations
Citations of this article
18Readers
Mendeley users who have this article in their library.

Abstract

Information technologies such as e-commerce and e-news bring overloaded information as well as convenience to users, cooperatives and companies. Recommender system is a significant technology in solving this information overload problem. Due to the outstanding accuracy performance in top-N recommendation tasks, two-step recommendation algorithms are suitable to generate recommendations. However, their recommendation lists are biased towards popular items. In this paper, we propose a user based two-step recommendation algorithm with popularity normalization to improve recommendation diversity and novelty, as well as two evaluation metrics to measure diverse and novel performance. Experimental results demonstrate that our proposed approach significantly improves the diversity and novelty performance while still inheriting the advantage of two-step recommendation approaches on accuracy metrics.

References Powered by Scopus

Item-based collaborative filtering recommendation algorithms

7501Citations
N/AReaders
Get full text

Neural collaborative filtering

5491Citations
N/AReaders
Get full text

Cumulated gain-based evaluation of IR techniques

3680Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Survey of similarity functions on neighborhood-based collaborative filtering

60Citations
N/AReaders
Get full text

Survey on the Objectives of Recommender Systems: Measures, Solutions, Evaluation Methodology, and New Perspectives

35Citations
N/AReaders
Get full text

Multi-factor ranking method for trading-off accuracy, diversity, novelty, and coverage of recommender systems

16Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Niu, K., Zhao, X., Li, F., Li, N., Peng, X., & Chen, W. (2019). UTSP: User-Based Two-Step Recommendation with Popularity Normalization towards Diversity and Novelty. IEEE Access, 7, 145426–145434. https://doi.org/10.1109/ACCESS.2019.2939945

Readers' Seniority

Tooltip

Lecturer / Post doc 4

50%

PhD / Post grad / Masters / Doc 3

38%

Researcher 1

13%

Readers' Discipline

Tooltip

Computer Science 6

55%

Engineering 3

27%

Business, Management and Accounting 2

18%

Save time finding and organizing research with Mendeley

Sign up for free