Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via reducing the shift between the data distributions. Existing cross-domain sentiment classification methods need to distinguish pivots, i.e., the domain-shared sentiment words, and non-pivots, i.e., the domain-specific sentiment words, for excellent adaptation performance. In this paper, we first design a Category Attention Network (CAN), and then propose a model named CAN-CNN to integrate CAN and a Convolutional Neural Network (CNN). On the one hand, the model regards pivots and non-pivots as unified category attribute words and can automatically capture them to improve the domain adaptation performance; on the other hand, the model makes an attempt at interpretability to learn the transferred category attribute words. Specifically, the optimization objective of our model has three different components: 1) the supervised classification loss; 2) the distributions loss of category feature weights; 3) the domain invariance loss. Finally, the proposed model is evaluated on three public sentiment analysis datasets and the results demonstrate that CAN-CNN can outperform other various baseline methods.

Transfer learning has gained a lot of attention and interest in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different domains such that the divergence between domains can be reduced with the new representation. Recently, deep learning has been proposed to learn more robust or higher-level features for transfer learning. In this article, we adapt the autoencoder technique to transfer learning and propose a supervised representation learning method based on double encoding-layer autoencoder. The proposed framework consists of two encoding layers: one for embedding and the other one for label encoding. In the embedding layer, the distribution distance of the embedded instances between the source and target domains is minimized in terms of KL-Divergence. In the label encoding layer, label information of the source domain is encoded using a softmax regression model. Moreover, to empirically explore why the proposed framework can work well for transfer learning, we propose a new effective measure based on autoencoder to compute the distribution distance between different domains. Experimental results show that the proposed new measure can better reflect the degree of transfer difficulty and has stronger correlation with the performance from supervised learning algorithms (e.g., Logistic Regression), compared with previous ones, such as KL-Divergence and Maximum Mean Discrepancy. Therefore, in our model, we have incorporated two distribution distance measures to minimize the difference between source and target domains in the embedding representations. Extensive experiments conducted on three real-world image datasets and one text data demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.

Most existing rat able aspect generating methods for aspect mining focus on identifying and rating aspects of reviews with overall ratings, while huge amount of unrated reviews are beyond their ability. This drawback motivates the research problem in this paper: predicting aspect ratings and overall ratings for unrated reviews. To solve this problem, we novelly propose a topic model based on Latent Dirichlet Allocation with indirect supervision. Compared with the previous bag-of-words representation of review documents, we utilize the quad-tuples of (head, modifier, rating, entity) to explicitly model the associations between modifiers and ratings. Specifically, our solution for aspect mining in unrated reviews is decomposed into three steps. Firstly, rat able aspects are generated over sentiments from training reviews with overall ratings. Afterwards, inference of aspect identification and rating for unrated reviews are provided. Finally, overall ratings are predicted for unrated reviews. Under this framework, aspect and sentiment associations are captured in the form of joint probabilities through a generative process. The effectiveness of our approach is testified on a real-world dataset crawled from Trip Advisor http://www.tripadvisor.com/, and extensive experiments show that our method significantly outperforms state-of-the-art methods.