Text sentiment analysis is mainly to detect the sentiment polarity implicit in text data. Most existing supervised learning algorithms are difficult to solve the domain adaptation problem in text sentiment analysis. The key of cross-domain text sentiment analysis is how to extract the domain shared features of different domains in the deep feature space. The proposed method uses denosing autoencoder to extract the deeper shared features with better robustness. In addition, Wasserstein distance-based domain adversarial and orthogonal constraints are combined for better extracting the deep shared features of the different domain. Finally, the deep shared features are used for cross domain sentiment classification. The experimental results on the real data sets show that the proposed method can better adapt to domain differences and achieve higher accuracy.
CITATION STYLE
Cai, G., Lin, Q., & Chen, N. (2020). Cross-Domain Text Sentiment Classification Based on Wasserstein Distance. In Advances in Intelligent Systems and Computing (Vol. 895, pp. 280–291). Springer Verlag. https://doi.org/10.1007/978-3-030-16946-6_22
Mendeley helps you to discover research relevant for your work.