Weibo Recommendation Algorithm Based on Tag Clustering and User Preference
Huiming Che, Liancheng Xu · 2019
The microblog recommendation algorithm has the problems of cold start, sparse data and low accuracy. To solve this problem, this paper proposes a microblog recommendation algorithm based on label clustering and user preference. Firstly, the user tag is obtained as the user's preference. The user's preference is divided by the tag clustering algorithm to obtain the similarity between the users. Secondly, the important user of the user is obtained by the PageRank algorithm, and the user is obtained according to the relationship between the users. The important user preference similarity, in order to obtain user preferences indirectly, the combination of the two to calculate the similarity of user preferences. The experimental results show that the improved algorithm can mine user preferences and improve the recommendation quality.