Multi-dimensional emotion intensity value calculation method fusing emoticons and short texts

Abstract

The invention relates to a multi-dimensional emotion intensity value calculation method fusing emoticons and short texts. The method comprises the following steps: (1) constructing an emoticon dictionary; (2) extracting emoji features, and calculating a multi-dimensional emotion intensity value; calculating a multi-dimensional emotion intensity value of the text and Emoji combined part; and calculating a multi-dimensional emotion intensity value of the network comment statement: for the emotion intensity of the social network comment statement, considering the multi-dimensional emotion intensity values of the two parts, and obtaining the multi-dimensional emotion intensity value of the statement by weighting the emotion intensity of the two parts.

Description

technical field [0001] The invention relates to a method for calculating multi-dimensional emotional intensity values ​​oriented to network comments and integrating emoticons and short texts. Background technique [0002] The emotional behavior analysis of social networks plays an important role in many fields such as product reviews, public opinion monitoring, and information prediction. In the field of e-commerce, sentiment analysis can provide users with historical sentiment evaluation summaries of products, which is convenient for users to quickly understand product evaluation information. In the field of public opinion monitoring, since people have the right to speak on the Internet, various topics and opinions related to the national economy and people's livelihood can be released at any time. Virtual social networks and real social interactions have a greater and greater direct impact on society, directly affecting the country. security and social stability. Detecti...

AI Technical Summary

Problems solved by technology

[0003] Some early methods used rule-based and machine learning-based methods to conduct sentiment analysis only on short texts. At present, some works combine text with Emoji for sentiment classification, and emoticons, as important emoticons, are used in more and more media comments It is used in Chinese social networks. The sentiment analysis in Chinese social networks almost all adopts filtering processing for kaomoji, which results in the lack of emotional characteristics, and it is impossible to accurately judge the impact of the used kaomoji on the sentiment of social network comments.

Images