The Study of An Integrated Algorithm for Identifying Fine-grained Sentiment of Micro-blog

Currently,most sentiment analysis of micro-blog has been focused on coarse-grained sentiment analysis,but fine-grained sentiment is better for reflecting the opinion of the public when they are facing the social focus.Therefore,an integrated algorithm which is a combination of Naive Bayes and K-Nearest Neighbor is put forward,which has been applied to the sentiment recognition and analysis of sina microblog.First,microblog is classified into two types: sentiment and non-sentiment by using Bayesian classification algorithm.And then a 21 dimension vector is built for the predicted and the marked microblog on the basis of the sentiment ontology.Finally the vector similarity between the predicted microblog and the marked ones is calculated by using K-nearest neighbor algorithm,which could help to identify the fine-grained sentiment of microblog.Experimental results show that a good result is achieved in fine-grained sentiment recognition of microblog based on the combination of Naive Bayes and K-nearest neighbor algorithm.