Design of Recommender Systems Exploiting Diversity Based on Network Representation Learning 


Vol. 45,  No. 5, pp. 899-902, May  2020
10.7840/kics.2020.45.5.899


PDF Full-Text
  Abstract

Recently, it has been actively studied how to develop recommender systems using network embedding. However, most studies were carried out in the sense of improving the recommendation accuracy, and thus approaches on exploiting diversity, thought of as another important measure in enhancing the quality of experiences, have been underexplored. In this letter, we propose a collaborative filtering model that improves the diversity based on network embedding. It is demonstrated that the proposed method is beneficial in terms of intra-list distance and aggregate diversity at the cost of slight accuracy reduction.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

C. Kwak, C. Seo, W. Shin, "Design of Recommender Systems Exploiting Diversity Based on Network Representation Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 899-902, 2020. DOI: 10.7840/kics.2020.45.5.899.

[ACM Style]

Changsoo Kwak, Changwon Seo, and Won-Yong Shin. 2020. Design of Recommender Systems Exploiting Diversity Based on Network Representation Learning. The Journal of Korean Institute of Communications and Information Sciences, 45, 5, (2020), 899-902. DOI: 10.7840/kics.2020.45.5.899.

[KICS Style]

Changsoo Kwak, Changwon Seo, Won-Yong Shin, "Design of Recommender Systems Exploiting Diversity Based on Network Representation Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 899-902, 5. 2020. (https://doi.org/10.7840/kics.2020.45.5.899)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880