Emotion analysis method and device and electronic equipment

Abstract

The invention discloses an emotion analysis method and device and an electronic device. The method comprises the steps of determining a to-be-analyzed sentence in a to-be-analyzed text; performing subject matching on each to-be-analyzed sentence based on a preset subject information base, wherein the preset subject information base comprises multiple pieces of subject information; when the targetsubject is matched in the to-be-analyzed sentence, determining the weighting coefficient of each word in the to-be-analyzed sentence to the target subject by utilizing a subject emotion self-attentionmechanism, and forming the subject emotion self-attention mechanism by combining dependency grammar modeling; determining emotion words in the to-be-analyzed sentence and polarity of the emotion words; utilizing the emotion words, the polarity of the emotion words and the weighting coefficient to determine the emotion value of the to-be-analyzed sentence to the target subject; and combining the emotion values of all the to-be-analyzed sentences matched with the target subject in the to-be-analyzed text, and determining the emotion value of the to-be-analyzed text for the target subject. According to the invention, the emotional tendency of the target subject in the text can be accurately determined.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a sentiment analysis method, device and electronic equipment. Background technique [0002] In recent years, with the vigorous development of the Internet, the information generated by people through the Internet is exploding exponentially. Every day, users use the Internet, especially social media networks (such as Weibo, WeChat official account, commentary news, etc.), to generate a large amount of data with emotional information on people, events, products, companies, etc. [0003] Existing sentiment analysis methods mainly focus on the overall sentiment mining of texts at the chapter, paragraph and sentence levels. Sentiment analysis tasks at this level often result in inaccurate analysis results and low correlation due to the coarse granularity of emotion and the lack of correlation modeling with emotional subjects. For example, for "A mobile phone is easier to use t...

AI Technical Summary

Problems solved by technology

Sentiment analysis tasks at this level often result in inaccurate analysis results and low correlation due to the coarse granularity of emotions and the lack of correlation modeling with emotional subjects.

For example, for "A mobile phone is easier to use than B mobile phone", the overall sentence-level emotion is positive emotion, but specific to the subject of B mobile phone, the actual emotion expressed is negative emotion, and the analysis of emotional tendency is not accurate enough at this time

Images