Deep belief network-based short text feature optimization and sentiment analysis method

Abstract

The invention discloses a deep belief network-based short text feature optimization and sentiment analysis method. The method comprises the following steps of: 1, obtaining a microblog short text corpus set, a thesaurus, semantic progressive associated words, microblog expression dictionary and a word segmentation model; 2, expanding and reconstructing short texts; 3, carrying out word segmentation and preprocessing on the short texts; 4, constructing a word similarity calculation model; 5, expanding feature vectors of the short texts; 6, self-adaptively extracting an expanded candidate feature set on the basis of a feature depth of a deep belief network; 7, carrying out classified training on the feature set obtained by the deep belief network by utilizing a machine learning classification algorithm so as to obtain a classification and prediction model; and 8, carrying out sentiment annotation on a test data set by utilizing the classification and prediction model. The method is capable of finding potential feature semantic information more effectively and improving the quality of sentiment feature extraction so as to improve the correctness of sentiment classification.

Description

technical field [0001] The invention belongs to the field of text information processing, and in particular relates to a short text feature extraction and sentiment analysis method based on a deep belief network. Background technique [0002] The main content of sentiment analysis is to discover the subjective opinions carried in the text, including the thoughts, hobbies, and emotional expressions of the information subject. It is a multidisciplinary task involving NLP (Natural Language Processing), IR (Information Retrieval), AI (Artificial Intelligence) and many other fields. [0003] The research on sentiment analysis of short texts is a new direction developed along with the emergence of new social tools at home and abroad. Compared with the analysis of opinions and sentiment tendencies of traditional texts, short texts are full of expressions due to their short content, sparse features, and random grammatical expressions. Elements and other non-standard expression word...

AI Technical Summary

Problems solved by technology

[0009] To sum up, the rule-based sentiment analysis method cannot effectively utilize the potential semantic information of the text, and the traditional machine learning feature extraction method is mainly based on the method of probability statistics, which has inherent defects. In order to make up for the shortcomings of these methods, the present i

Images