Text generation and evaluation system with emotion tags based on deep learning

Abstract

The invention relates to a text generation and evaluation system with emotion tags based on deep learning, in particular to a text generation and evaluation system with an emotion label based on deeplearning, which is realized by the following technical scheme: generating a comment introduction model through a data introduction model, and finally scoring and realizing visualization so that high-quality text with emotional colors can be generated. Compared with other existing evaluation systems at present, the invention has the advantages that the quality of the generated text is better, the optimal selection of the text is realized, a text visualization interaction terminal is designed, and model optimization and method verification are facilitated.

Description

technical field [0001] The invention relates to an evaluation system, in particular to a deep learning-based text generation and evaluation system with emotional labels. Background technique [0002] With the rise of social networks such as Facebook and Twitter, the Internet has not only become an important source of information for people, but also a platform for people to express their opinions. By commenting on hot events, expressing film review opinions, describing product experience, etc. in blogs, topics, Twitter and other online communities, a large amount of text information with emotional tendencies is generated, and by performing sentiment analysis on these text information, we can better understand User behavior, discovering users' inclinations to products, degree of attention to hot events, etc. With the rapid increase of information scale, it is impossible to complete this task only by manual processing, which promotes a research hotspot in the field of natural...

AI Technical Summary

Problems solved by technology

The shallow learning method has a small amount of calculation and is easy to implement, but due to the limitation of the expression ability of complex functions, the generalization ability of complex classification problems is restricted

In order to make up for this defect, artificially constructed features are introduced into this model, such as the use of artificially labeled sentiment dictionaries, syntax and grammatical analysis, etc. Although these methods can effectively improve the accuracy of text sentiment analysis, due to the need for too much Manually labeling data is time-consuming and labor-intensive, and requires certain prior knowledge. Therefore, with the continuous development of the scale of the Internet, the scale of text data continues to expand, which limits the development of these methods.

Images