Short-text content classification method and system

Abstract

The invention discloses a short-text content classification method. The method includes: obtaining short-text contents of a social network platform; obtaining context emotion feature values and a priori emotion feature values of the short-text contents; using model training to generate a word vector of the short-text contents; utilizing multi-window convolution operations to obtain semantic relationships of the short-text contents of different granularities, and combining pooling operations to abstract semantic representations of the short-text content from different levels; using a bi-directional long-term memory network to obtain a semantic representation of the short-text contents; and combining different-level emotion feature vectors to obtain an output vector, using a function to carry out calculation on the output vector to obtain a value of probability that the short-text contents belong to one or more content categories, and using a content category, of which a value of probability is highest, as the category of the short-text contents. The invention also discloses a short-text content classification system, which can realize the aforementioned short-text content classification method.

Description

technical field [0001] The present invention relates to the technical field of information processing, and in particular to a short text content classification method and system based on a deep neural network. Background technique [0002] Emerging social media represented by Weibo has become an important medium for Internet users to obtain news information, social interaction, self-expression, share opinions, disseminate information and social participation. The main platform for dissemination. As of September 2017, the monthly active users of Twitter, a global microblogging service site, reached 330 million, while the monthly active users of Sina Weibo, a Chinese microblogging platform, reached 376 million and 165 million daily active users. Hundreds of millions of active users come from different social and cultural backgrounds and spread all over the world, generating a large amount of text information containing users' opinions and emotions every moment. [0003] Pote...

AI Technical Summary

Problems solved by technology

[0004] However, due to the short text of Weibo, incomplete grammatical structure, random and noisy expressions, the classification of Weibo texts faces great challenges.

The existing classification methods mainly use manual methods to construct classification features, and the bag-of-words model is often used for classification features, which is difficult to describe word order information, and faces the problems of dimension explosion and data sparseness

In addition, the text of Weibo often has "explicit praise and implicit criticism" or implicit expressions, and it is difficult to discover and describe such implicit semantic relationships by artificially constructing features.

Images