GCN-based cross-domain sentiment analysis method under the framework of lifelong learning

Abstract

The present invention provides a GCN-based cross-domain sentiment analysis method under the lifelong learning framework, and relates to the field of cross-domain sentiment classification in natural language processing. The GCN-based cross-domain sentiment analysis method under the lifelong learning framework in the present invention is implemented by the following process: A cross-domain sentiment classification algorithm based on graph convolutional neural network, namely CDS-GCN, is proposed. On the basis of proposing CDS-GCN, combined with the idea of ​​lifelong learning, a cross-domain sentiment classification algorithm based on graph convolutional neural network under the lifelong learning framework is proposed. Namely LLCDS-GCN, these features make lifelong learning different from related learning tasks such as transfer learning or multi-task learning. It breaks the limitation of isolated learning and alleviates the time-consuming and laborious impact of manual labeling data. These features are consistent with cross-domain sentiment classification. The original intention of the task coincides with each other.

Description

technical field [0001] The invention relates to the field of cross-domain sentiment classification in natural language processing, in particular to a GCN-based cross-domain sentiment analysis method under a lifelong learning framework. Background technique [0002] The popularization of the Internet has brought a larger user group to merchants, and also brought more user feedback information. Users can easily express their views and opinions on the products they use or receive services on the Internet, such as a large number of product reviews. Can be easily obtained on Douban (movie reviews), Amazon (book reviews), Meituan (restaurant reviews), etc. Document-level sentiment classification refers to classifying a given review according to the sentiment expressed by the review author. The task is very important. First of all, for merchants, consumers’ evaluations of products reflect their likes and dislikes for product quality or services. Secondly, consumers who have not pur...

AI Technical Summary

Problems solved by technology

[0003] Problems: Traditional supervised learning algorithms have been proven to be effective in dealing with sentiment classification problems, and are widely used in the task of predicting the sentiment polarity of reviews given a domain

But the graph structure is different from the matrix structure, and the situation near each node may be different from each other, so it does not have translation invariance

Images