Public Sentiment Toward Personalized Recommendation System: Evidence in Chinese Social Media
(A2025-125697)

AUTHORS

Lewis Bingwen Huang, University of Macau; Joseph Sy-Changco, University of Macau

ABSTRACT

Personalized Recommendation Systems (PRS) are algorithmic tools designed to deliver tailored content based on users’ digital footprints, gaining attention in recent research. This study examines Chinese public sentiment toward PRS using user-generated content from Weibo, employing sentiment analysis and topic modeling. Findings reveal a neutral to positive sentiment overall but indicate declining satisfaction over time. PRS enhances fanbase growth, social engagement, and user experience but raises concerns about filter bubbles, annoying ads, and privacy. Recommendations include diversifying content and increasing algorithm transparency to mitigate negative sentiment. Retailers should address declining PRS effectiveness by reassessing strategies and resource allocation.