Sentiment classification of Chinese Weibo based on extended sentiment dictionary and organisational structure of comments

Sentiment classification can provide the decision support of social applications such as trend judgment, public opinion monitoring, etc. However, accuracy sentiment for Chinese Weibo is still not satisfactory due to complexity Chinese. In addition, affected by different organisational structure levels, tendency fewer Comments may be judged opposite. To solve problem above, this paper presents a model based on extended dictionary and comments. First, using seven dictionaries, which include base six additional dictionaries. Then, sets rules are constructed, inter-sentence rules. Finally, comments three hot topics crawled used make data calculation. Accordingly, result calculation, completed. The effectiveness proposed verified through comparison experiments, experimental results also discussed.