Comment emotion classification method and system based on deep hybrid model transfer learning

Abstract

The invention provides a comment emotion classification method and system based on deep hybrid model transfer learning. The comment emotion classification method comprises the following steps: Step S1, collecting a commodity comment and preprocessing a source domain data sample set of the commodity comment; Step S2, mapping the preprocessed data into a word vector; Step S3, pre-training the sourcedomain data sample set of the commodity review with the depth mixing model; Step S4, fine-tuning the depth mixing model for the target domain data sample set of the commodity review; and Step S5, classifying the emotion of the commodity comment in the target domain. Tthe training speed is fast and the training difficulty is low, the invention only need several rounds of training to obtain high classification accuracy, and also can obtain good classification effect when the data set with more noise or less quantity is trained, and has little dependence on the data set and good robustness. Theinvention also effectively improves the transferability, and achieves the purpose of improving the classification accuracy after the transfer learning.

Description

technical field [0001] The present invention relates to a comment sentiment classification method, in particular to a comment sentiment classification method based on deep mixed model transfer learning, and to a comment sentiment classification system using the comment sentiment classification method based on deep mixed model transfer learning. Background technique [0002] In the prior art, the sentiment classification of product reviews mainly includes the following two methods: the first one is a cluster-based cross-domain transfer learning method for product review sentiment classification, the principle of which is to use the irrelevant relationship between the source domain and the target domain. Words are used as an intermediary, using the similarity of words in the source domain and the target domain, and using the spectral clustering algorithm to arrange domain-related words in different fields into a unified cluster. Differences between related terms in the dataset...

AI Technical Summary

Problems solved by technology

At the same time, the training difficulty of this method is also relatively large, especially if the samples in the data (especially the target domain data) contain a lot of noise at the beginning of the preliminary training, and the number of iterations is not well controlled, the accuracy of the classifier will be greatly reduced.

From a practical point of view, this migration method has poor robustness and generally low accuracy.

Images