Design and Implementation of Weibo Sentiment Analysis Based on LDA and Dependency Parsing

• Published in: China communications Vol. 13; no. 11; pp. 91 - 105
• Main Author: Yonggan Li Xueguang Zhou Yan Sun Huanguo Zhang
• Format: Journal Article
• Language: English
• Published: China Institute of Communications 01.11.2016; Computer School of Wuhan University, Wuhan University, Wuhan 430079, China; The Key Laboratory of Aerospace Information Security and Trust Computing, Ministry of Education, Wuhan 430072, China%Department of Information Security, Navy University of Engineering, Wuhan 430033, China%Unit Number of 92941, PLA, Huludao, Liaoning Province 125000, China
• Subjects: dependency parsing; Earth; emotion expression extraction; emotion tendency classification; information content security; information security; LDA; Semantics; sentiment analysis; Tagging; 内容安全; 句法分析; 合并算法; 吉布斯抽样; 情感表达; 网络空间安全; 设计; emotion expression extraction; information security; information content security; dependency parsing; sentiment analysis; emotion tendency classification
• ISSN: 1673-5447
• DOI: 10.1109/CC.2016.7781721

Information content security is a branch of cyberspace security. How to effectively manage and use Weibo comment information has become a research focus in the field of information content security. Three main tasks involved are emotion sentence identification and classification,emotion tendency classification,and emotion expression extraction. Combining with the latent Dirichlet allocation（LDA） model,a Gibbs sampling implementation for inference of our algorithm is presented,and can be used to categorize emotion tendency automatically with the computer. In accordance with the lower ratio of recall for emotion expression extraction in Weibo,use dependency parsing,divided into two categories with subject and object,summarized six kinds of dependency models from evaluating objects and emotion words,and proposed that a merge algorithm for evaluating objects can be accurately evaluated by participating in a public bakeoff and in the shared tasks among the best methods in the sub-task of emotion expression extraction,indicating the value of our method as not only innovative but practical.