Research on topics trends based on weighted K-means
Hongzhi Tao, Jianfeng Li, Tao Luo, Cong Wang · 2017
To capture the trends of concerned topics in specific field, people often use topic discovery methods to get this goal. The traditional topic discovery algorithms are generally divided into two types, text clustering algorithm and text topic model. The former lacks of attention on semantic information, and the latter always ignores relativity of the topic. These affect the topic discovery and topic trend. Therefore, combining with the keywords combination and Word2Vec model to strength expression of semantic information in topic clustering, this article sets weighted K-means algorithm for topic discovery. The results show our weighted K-means algorithm can get good clustering effect, and have improved semantic expression and topic relativity, it can also be used to filter noise data. In particular, the algorithm has better performance in a specific topic field.