Bimodal man-man conversation sentiment analysis system and method thereof based on machine learning

Abstract

The invention comprises a bimodal man-man conversation sentiment analysis system and a bimodal man-man conversation sentiment analysis method based on machine learning. The bimodal man-man conversation sentiment analysis system is characterized by comprising a speech recognition module, a text deep-layer feature extraction module, a speech segmentation module, an acoustic feature extraction module, a feature fusion module and an sentiment analysis module, wherein the speech recognition module is used for recognizing speech content and a time label; the text deep-layer feature extraction module is used for completing the extraction of text deep-layer word level features and text deep-layer sentence level features; the speech segmentation module is used for segmenting single sentence speech from entire speech; the acoustic feature extraction module is used for completing the extraction of acoustic features of the speech; the feature fusion module is used for fusing the obtained text deep-layer features with the acoustic features; and the sentiment analysis module is used for acquiring sentiment polarities of the speech to be subjected to sentiment analysis. The bimodal man-man conversation sentiment analysis method can integrate the text and audio modals for recognizing conversation sentiment, and fully utilizes features of word vectors and sentence vectors, thereby improving the precision of recognition.

Description

technical field [0001] The invention relates to the field of human-computer emotional interaction, in particular to a machine learning-based dual-mode human-to-human dialogue emotion analysis system and a method thereof. Background technique [0002] With the development of society and the advancement of network technology, people communicate more and more frequently, and the communication methods are more and more diverse. Accurately identifying the emotions in everyone's conversations is of great significance for call centers and other telephone service industries. . However, people's emotional expression in dialogue is very complicated. [0003] Sentiment words expressing emotion in dialogue can be divided into direct emotion words and negative emotion words. Sometimes some people already have negative emotions during the conversation, but because of their politeness and demeanor, they will not use direct emotional words to fully express their inner emotions, or use a t...

AI Technical Summary

Problems solved by technology

It is very difficult to identify latent emotional words and latent emotions, and a single recognition of a certain feature is not comprehensive for sentiment analysis. At the same time, traditional feature extraction methods are generally chi-square test, information gain, etc. The features extracted in this way are It is more superficial and cannot be analyzed using contextual information; finally, the current recognition methods mainly include: the methods for text recognition alone, most of which use word frequency-inverse document frequency and other models to perform emotional recognition on text, and most of them need to preprocess the text , while the correct rate is low in multilingual and multi-category recognition

Images