Abstract
In this paper, we introduce a novel model called BGAC for text semantic analysis task. The proposed network is a new integration of two Bi-GRU, self-Attention mechanism and Capsule network architecture. In our experiment on the task of sentiment analysis in dataset IMDB (a public film review dataset), our model achieve the state-of-the-art results. We compare it with six other deep learning models, such as LSTM, CNN, GRU, BI-GRU, CNN+GRU and GRU+CNN. The results of the experiments show that the experimental effect of the bidirectional GRU fusion self-attention mechanism and the capsule network outperforms than the other six neural network models. In addition, the experiments show that combination of GRU with CNN is better than that combination of CNN and GRU, and the combination of CNN with GRU performs better than employ CNN model alone. The accuracy of using single CNN is successively higher than that of LSTM, BI-GRU and GRU model. Our model which the combination of the BI-GRU, Attention and Capsule network introduced in this paper achieves the highest accuracy, precision and F1 score. In conclusion, the bidirectional GRU with self-attention mechanism and capsule network model significantly improves the accuracy of text sentiment classification task.
Highlights
With the rapid development of the Internet, the fast and convenient ways to purchase online products, and the diversification of types, have made people increasingly rely on online purchases
The results prove that the effect of the capsule network on multi-label text classification tasks has been significantly improved
The experimental comparison results of IMDB data set are shown in Table 3 below
Summary
With the rapid development of the Internet, the fast and convenient ways to purchase online products, and the diversification of types, have made people increasingly rely on online purchases. Cheng Yan et al [2] proposed a neural network model based on the attention mechanism of multi-channel CNN and bidirectional gated recurrent unit This model can focus on the words that are important for emotional polarity classification in the sentence through the attention mechanism, and combines the advantages of CNN to extract local features of text and Bi-GRU network to extract long text context semantic information, which improves the model's text feature extraction ability. Pang et al [18] tried different machine learning algorithms on a film review data set, and achieved an accuracy of 82.9% on a large number of texts through analysis and comparison of characters. Gangemi et al [24] proposed a method for identifying opinion holders and subjects using an unsupervised framework
Sign-in/Register to view highlights & summary 
Published Version (
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