Abstract
Aspect-level sentiment analysis aims at identifying the sentiment polarity of target in the context. In most of the previous sentiment analysis models, there usually exists the problem of insufficient extraction capability of local features and long-distance dependency features. To solve the above problem, in this paper, we propose an improved model (called ADeCNN) for aspect-level sentiment analysis, by incorporating the attention mechanism into the deformable CNN model. In ADeCNN, we use deformable convolutional layers and bi-directional long short-term memory network (Bi-LSTM), combined with sentence-level attention, to extract sentiment features, and to break through the limitations of the model's long-distance dependency feature extraction capability. We then use a gated end-to-end memory network (GMemN2N) to integrate the target into the sentiment feature extraction process, so as to obtain sentiment features. And finally, we obtain the corresponding sentiment analysis results through the classifier. In addition, in order to solve the problem that the same words have large differences in the polarity of sentiments expressed in different targets, the model is also constructed with the ability to generate different attention weights based on target to assist sentiment analysis, with the aim of further enhancing the correlation between the target and the words in the sentence. We setup experiments to demonstrate the functionality effectiveness and performance gains of ADeCNN, based on the SemEval 2014 Task4 and SemEval 2017 Task4 datasets. Extensive experimental results show that ADeCNN outperforms its competitors, producing an arresting increase of the classification accuracy on all the three datasets of Laptop, Restaurant, and Twitter.
Highlights
With the rapid development of information technology, the Internet has become an important way for people to obtain information and express their opinions, and a large amount of text data has accumulated on the Internet
In ADeCNN, we introduce the deformable convolutional neural network (CNN) that is mainly applied in the image processing domain into the field of sentiment analysis, and adapt deformable convolutional layers with bi-directional long short-term memory network (Bi-LSTM), so that it is suitable for extracting sentiment features from one-dimensional text, thereby obtaining stronger feature extraction capability than the standard CNN
COMPARISON WITH BASE MODELS 1) BASE MODELS We compare the ADeCNN with the baseline models to show the effectiveness of the deformable CNN layer
Summary
With the rapid development of information technology, the Internet has become an important way for people to obtain information and express their opinions, and a large amount of text data has accumulated on the Internet. Hu and Liang [6] incorporated a deep attention mechanism into the LSTM model, and obtained aspect-level sentiment analysis result by focusing attention on word vectors related to the target. This paper introduces DeCNN for local feature extraction of text sentiment, so that more valuable features can be input into subsequent models for sentiment analysis to obtain better results. Most of the existing aspect-level sentiment analysis models used CNN to perform the first round of sentiment features extraction, and further extract the contextual features of the text by connecting the LSTM layer [17]–[19]. By expanding the scope of convolution kernels and RoI pooling, DeCNN enables the model to adaptively locate data points that are closely related to the current data point in feature extraction, thereby more effectively capturing important information features to achieve better extraction effect
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
