Neural Feedback Text Clustering With BiLSTM-CNN-Kmeans

Text clustering is a very important technique in the field of data mining. It is widely used in information retrieval and text integration. Most existing studies focus on the optimization of feature extraction methods or clustering algorithms separately. In this paper, we propose a neural feedback clustering algorithm combining bidirectional long short-term memory and convolutional neural network with kmeans method. Unlike previous papers, the proposed algorithm treats feature extraction and clustering as a united process, where clustering results can be used as feedback information to dynamically optimize the parameters of networks. Experimental results show that the proposed algorithm achieves significant improvements compared with other existing text clustering algorithms and has a certain degree of noise robustness.