Chinese clause emotion polarity distinguishing method based on context

Abstract

The invention discloses a Chinese clause emotion polarity distinguishing method based on a context. The method comprises the following steps of: (1) marking a Chinese word and the work property in a Chinese clause to obtain a respective characteristic value, a privative, an adverb and an emotion word in each Chinese clause; matching the emotion word and the emotion word of the Chinese clause; determining the emotion polarity of the emotion word to obtain the emotion polarity of the Chinese clause; (2) calculating the emotion strength degree of each Chinese clause according to the adverb in the Chinese clause; and (3) extracting a conjunction in the Chinese clause; and with regard to three adjacent Chinese clauses, revising the emotion polarity of the Chinese clause of the step (1) according to the conjunction and the emotion strength degree of the adjacent Chinese clauses. According to the Chinese clause emotion polarity distinguishing method based on the context, the working amount of manual work can be obviously reduced and the accuracy in distinguishing the emotion of the Chinese clauses in the complicated language environment can be effectively improved.

Description

technical field [0001] The invention relates to the field of emotional calculation of Chinese clauses, in particular to a method for discriminating the emotional polarity of Chinese clauses based on context. Background technique [0002] With the advent of the Web2.0 era, Internet interactive technology has developed rapidly, and a large number of comment information with subjective emotions has appeared on the Internet. These commentary information often reflect people's views and opinions on things or events. For example, on an e-commerce platform, a transaction may correspond to a text review, which usually indicates the buyer's opinion on product quality, seller service, logistics speed, etc., so these reviews contain a lot of useful information , has important reference value and practical significance for merchants' advertising, marketing, business decisions, and buyers' shopping choices. At present, the method of simply using manual analysis and screening can no lon...

AI Technical Summary

Problems solved by technology

[0005] At present, there are many researches on the emotional polarity discrimination at the word level, text level and massive data level in the academic circles, but few people are involved in the sentimental discrimination research at the sentence level.

At present, the existing sentence-level emotional polarity discrimination mostly adopts strict matching algorithms based on vocabulary, statistical prediction or machine learning, but pays little attention to the role of Chinese grammatical rules in emotional computing, especially the lack of context-based language Method of judging emotional polarity in environment

Images