Negative Emotion Event Detection for Chinese Posts on Facebook

As most people would like to post their articles in social network to express their feeling, it would benefit to collect and analyze these information to figure some signs before some misfortunes happened. Hence, in this paper, we propose a novel emotion analysis system not only to detect the Chinese posts with negative emotions on Facebook in time sequence but also extract the places related to those posts. 9820 posts from Facebook are used as a training set and 2334 posts from Facebook as testing samples to verify the system accuracy. Experimental results show that the precision of negative emotion classification of the proposed system is 74.8%, and the recall rate is 78.7%, both of the precision and recall the proposed system are better than traditional methods (SVM and Naïve Bayesian) 8%~17%. In addition, the proposed system is not only able to extract the posts with negative emotions, but also to find the correlation between emotion and places.