International Journal of Human-Computer Interaction, Год журнала: 2024, Номер unknown, С. 1 - 14

Опубликована: Дек. 27, 2024

This paper is to explore the influence of recommendation system on users' topic diversity. We construct a simulation that covers news closed-loop processes user profile generation, generation and delivery, selection browsing, update. Quantitative indicators were formulated assess diversity, encompassing both individual aggregate dimensions. Then compared effects diversity across three delivery methods. The results show with method self-selection, filtering-based popular significantly increase while having obstructive Various algorithms ways update profiles have slight impacts do not change relationships in trends. Lastly, we discussed relevant topics conjunction our conclusions.

Язык: Английский