Emotion analysis method based on rule and data network fusion

Abstract

The invention discloses an emotion analysis method based on rule and neural network fusion. The method comprises the steps that 1, a certain quantity of structured comments about a target object are acquired to form a to-be-analyzed corpus, and an emotion ontology base is obtained through semantic analysis generalization according to an emotion ontology base provided by an authority in combinationwith the corpus, wherein the emotion ontology base contains emotion limits and emotion degrees; 2, emotion word matching and an emotion word relation are preprocessed, word segmentation, text analysis and ontology base matching are performed on the corpus, emotion words in sentences are commented, and emotion information of the emotion words and an depending relation corresponding to a context are annotated, wherein the emotion information contains emotion strength of the words, emotion polarity and part-of-speeches of the emotion words; and 3, emotion calculation, feature fusion and emotiontendency judgment are performed. Through the method, emotion classification can be performed according to the context more precisely.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to a Chinese text sentiment analysis method, and provides a rule-based and neural network fusion sentiment analysis method. Background technique [0002] With the rapid development of Internet technology, a large number of information published by users about people, events, etc. , products and other target entity review information. Different from objective texts, these highly subjective commentary information contains public opinions on the above-mentioned target entities, and has very important reference value for potential users, businesses, and government departments. However, it is obviously costly, inefficient and difficult to collect and analyze these massive amounts of information manually. Text sentiment analysis technology, which uses computers to classify and extract unstructured text comments, emerges at the historic moment. [0003] At present, there are m...

AI Technical Summary

Problems solved by technology

Among them, the training of supervised and semi-supervised machine learning and neural network methods requires a certain number of labeled training samples. However, the manual labeling process is time-consuming, laborious and expensive, and unsupervised learning does not require labeling.

Images