Automatic personalized text summarization agent using generic relevance weight based on NMF

With the fast growth of the Internet access by user, it has increased the necessity of the personalized summarization method. This paper proposes automatic personalized text summarization agent using generic relevance weight based on non-negative matrix factorization (NMF). The proposed agent uses generic relevance weight to summarize generic summary so that it can extract sentences covering the major and sub topics of the search results with respect to user interesting. Besides, it can improve the quality of summarization since extracting sentences to reflect the inherent semantics of the search results by using the weighted NMF. The experimental results demonstrate that the proposed method achieves better performance the other methods.