A Model Training Method for Cross-Domain Sentiment Analysis Based on Convolutional Neural Networks

Abstract

The invention discloses a model training method for cross-domain sentiment analysis based on a convolutional neural network, belongs to the field of cross-domain sentiment classification, and aims tosolve the problem of cross-domain sentiment analysis. The method comprises: S1, preprocessing a text; S2, training a word vector model; S3, performing cross-domain model migration; wherein the step S3is carried out in sequence; a neural network model is trained through a source domain; migrating the trained model. Firstly, a weight value of a convolution kernel in a model is shared, a convolutionkernel weight trained in a source domain is used for extracting corresponding features in a target domain, a small part of data in the target domain is trained again, parameters of a full connectionlayer weight of the previously trained model are adjusted, and the effect is that model migration is conducted on a cross-domain emotion text.

Description

technical field [0001] The invention belongs to the field of cross-domain emotion classification, and relates to a model training method for cross-domain emotion analysis based on a convolutional neural network. Background technique [0002] In machine learning algorithms and data mining algorithms, an important assumption is that the training data and future training data must be in the same feature space and have the same data distribution. However, such an assumption does not hold true in practical application cases. Therefore, when the data distribution changes, most statistical models need to be reconstructed using training samples of the new data. In practical applications, the amount of data generated every day is unbelievable. According to the current data generation speed, 2.5 terabytes of data will be generated every day. If the data is collected again and the model is reconstructed, it will take At a very large cost, this is obviously impossible. Moreover, the ...

AI Technical Summary

Problems solved by technology

[0009] The researchers found that in sentiment classification, the classification effect is poor on data sets that belong to different fields for the training set and the test set.

Images