Topic Extraction for a Large Document Set with the Topic Integration

We propose here a method to extract topics from a large document set with topic integration from some small document sets. In order to extract topics, the Non-negative Matrix Factorization (NMF) is applied to document sets. It is useful to integrate the topics from some small document sets since the procedure of topic extraction with the NMF from a large document set takes a long time if the number of documents is large. In this paper, we have shortened the procedure time for the topic extraction from a large document set with the integration of topics extracted from respective some small document sets. In addition, an evaluation of our proposed method has been carried out with the compatibility of topics between the integrated topics and the topics from the large document set by the NMF directly, and the procedure times of the NMF.