Citation

Martono, Salsabila and Kusumo, Dana Sulistyo and Gandhi, Arfive and Haw, Su Cheng and Ng, Kok Why (2023) User Evaluation of Diversity and Novelty in the Redesigned Recommender List for an Indonesian E-Commerce Platform. Journal of System and Management Sciences, 13 (4). pp. 615-623. ISSN 1816-6075, 1818-0523

Text Vol.13.No.4.37.pdf - Published Version Restricted to Repository staff only Download (514kB)

Abstract

Recommendation systems have been widely used in e-commerce, to help users get information on products to be purchased. There have been many studies related to the evaluation of algorithm performance and aspects beyond the accuracy of the recommendation system. In this research, we analyzed the effect of the number of diversity and novelty aspects on the list of recommendation system items. We redesigned the interface of the recommendation list from one of the top Indonesian e-commerce. The experiment was conducted using within subject design with two different scenarios. We conducted follow-up interviews to dig deeper into what users thought about the two recommendation lists. From the results of the follow-up interview, 80% of the participants liked the second scenario, because the new items recommended gave them ideas to buy them. The results of this study show that the number of diversity and novelty items has a positive influence on user satisfaction. We also found that the user's perception of the recommendation list is influenced by the user's preferences and the user's goals when using the recommendation system.

Item Type:	Article
Uncontrolled Keywords:	Diversity, novelty, recommender system
Subjects:	Q Science > QA Mathematics > QA801-939 Analytic mechanics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	05 Sep 2023 02:56
Last Modified:	05 Sep 2023 02:56
URII:	http://shdl.mmu.edu.my/id/eprint/11692

Downloads

Edit (login required)