Considering the deficiencies in the existing emotional lexicons like too many manual interventions, lack of scalability and ignorance of dependency parsing in emotional computing, this paper first uses Word2Vec, cosine… Click to show full abstract
Considering the deficiencies in the existing emotional lexicons like too many manual interventions, lack of scalability and ignorance of dependency parsing in emotional computing, this paper first uses Word2Vec, cosine word vector similarity calculation and SO-PMI algorithms to build a public event-oriented Weibo emotional lexicon; then, it proposes a Weibo emotion computing method based on dependency parsing and designs an emotion binary tree based on dependency parsing, and dependency-based emotion calculation rules; and at last, through an experiment, it shows that this emotional lexicon has a wider coverage and higher accuracy than the existing ones, and it also performs a public opinion evolution analysis on an actual public event and the empirical results show that the algorithm is feasible and effective.
               
Click one of the above tabs to view related content.