Negative Emotion Detection with Consideration of Events and Places for Chinese Posts on Facebook and Applications

• Main Authors: Bor-Chen Huang, 黃柏誠
• Other Authors: Chung-Nan Lee
• Format: Others
• Language: en_US
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/93391358863315928915

碩士 === 國立中山大學 === 資訊工程學系研究所 === 104 === As the social network gains more popular, people would like to find the related information from social nets to figure out some signs before or after an incident occurred. In this thesis, we would like to classify the emotion of Chinese articles correctly and find the negative emotion. And we even aim to find out event cause and place that are extracted from Facebook or article content. Based on the lexicon based method we consider some factors like word relationship and event which effect the emotion in the article to propose a negative emotion classification rule, a normal sentence classification method and a negative emotion degree calculation scheme to support emotion classification and find out the degree of negative emotion. In the experiment, many posts from Facebook are extracted as test data and training data to verify accuracy of the proposed methods. Experimental results show that the proposed methods perform better compared to the traditional methods SVM and Naïve Bayesian (20% and 12%). In addition, the proposed methods also extract the events and places related to the posts. Then we apply the methods to two real cases, public emotion about an arbitrary event and personalization. Hence, the proposed methods are not only able to extract the posts with negative emotions, but also able to find out the cause of the events and related place in the posts.