Abstract: Currently in the news item recommendation system,usually using TF-IDF weighting technology combined with the cosine similarity measure,however,this technique does not take into account the actual semantics of the text itself,therefore,the paper propsed a new method based on the combination of contents and their semantic similarities. This method is a collection of synonyms and inverse document frequency combining semantic similarity using WordNet synset do similar calculations．Building user profiles for laboratory tests to verify the effectiveness of the method．Experimental results show that the proposed method outperforms the TF-IDF method.

Key words: News recommendation system,Semantic analysis,Semantic similarity,WordNet synset