Visualization and analysis based on Cite Space domestic feedback information recommendation application research

¹ Key Laboratory of Education Informatization, Ministry of Education, Yunnan Normal University, Chenggong, Kunming, China
^2,3 School of Information, Yunnan Normal University, Chenggong, Kunming, China

^* Corresponding author: sunyu@ynnu.edu.cn

Abstract

This study used Cite Space to analyse the domestic literature on feedback recommendation applications between 2003 and 2023. It is found that domestic scholars have conducted in-depth research in the areas of recommender systems, collaborative filtering, and implicit feedback, focusing on hotspots such as deep learning, matrix decomposition, and user feedback. Although the existing research focuses on improving the efficiency of information access and user satisfaction, the in-depth research on multi-source feedback integration methods still faces challenges. Future research can leverage new technologies such as deep learning to mine more user behaviour data and achieve more accurate personalized recommendations.