文献类型：期刊文献

英文题名：Using Hidden Markov model for identifying secure text of public opinion based on maximum entropy

作者：Ji, Dongya[1]; Zhang, Rui[2]

机构：[1] College of Business and Management, Shaoxing University, Shaoxing 312000, China; [2] College of Computer and Information Management, Zhejiang Gongshang University, Hangzhou 310018, China

年份：2010

卷号：6

期号：9

起止页码：2967

外文期刊名：Journal of Computational Information Systems

收录：EI(收录号：20104313324047)、Scopus(收录号：2-s2.0-77958092746)

语种：英文

外文关键词：Entropy - Hidden Markov models - Semantic Web

外文摘要：With wide spreading of network and quick developing of E-commerce, on-line reviews and news group discussions have become important parts in people's daily life. How to identify the semantic orientation of these reviews on sensitive topics, such as Taiwan independence and Falun Gong, and how to effectively control the public opinions and feelings on Internet, have been a focus for the research of information security. This paper presents a Hidden Markov Model Based on Maximum Entropy, for identifying the rules of integrating with statistics on the network security text. Experimental results show that the new algorithm improves the performance in precision and recall rate. ? 2010 Binary Information Press.