Identifying Opinion Sentences and Opinion Holders in Internet Public Opinion
Yufeng Zhang, Fei Long, Bin Lv · 2012
In this paper, we propose to automatic identify opinion sentences and opinion holders in Internet Public Opinion. We established a series of related resources to opinion analysis, such as opinion operator set etc. Based on these related resources, we use opinion operator as a key indicator to extract the opinion holder of the given sentence. With expanding the holders to noun phrases by pattern matching, the results of opinion holder automatic extraction are further improved. Our approach shows encouraging performance on opinion sentence and opinion holder identification. The experiment indicates that the accuracy rate reaches a higher degree.