Research on recognition of the emotional tendencies in web data mining

In the research of text emotional classification, although the method based on using characteristic words list and affective words list to identify the text emotional tendencies is simple and quick, but the accuracy is often poor. That's more the method cannot judgment the rhetorical relations. To solve this problem, this paper from the semantic comprehension point of view, using the dependency parsing method to process the sentiment phrases, feature phrase and negative sentence, and makes the text emotional classification possible. The experimental results show that this method can meet the practical need.