A Web Text Classification Algorithm Based on HowNet

According to the thinking of semantic analysis and the classification algorithm of Support Vector Machine (SVM), How Net was used for text classification to improve accuracy. For the polysemous word in web text, word sense disambiguation was used for selecting semantic item to compute words similarity, which clusters the words whose similarity above the target threshold and reduces the feature of text. A How Net-based web text classification algorithm was proposed, and experiments the performance of the Web text classification algorithm. Results of experiments show that the new algorithm can get better classified effect.