Semi-Supervised Semantic Dynamic Text Clustering Algorithm

In the traditional dynamic text clustering, the similar texts with different descriptions are divided into different groups; and the difference between the number of cluster categories and the number of real categories is obvious. Aiming at these problems, this paper proposes a semi-supervised semantic dynamic text clustering algorithm (SDCS). The algorithm captures the semantic relationship between texts by semantically representing the text, and dynamically learns the category semantics during the clustering process, so that the text can be accurately clustered according to semantics. At the same time, the algorithm uses the semi-supervised clustering algorithm to supervise the generation of new classes, and produces clustering results that are consistent with the actual situation. The experimental results show that the proposed algorithm is effective and feasible.