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.

Zhifei Hu. Sentiment Analysis of Film Reviews Based on BI-GRU+Attention+Capsule Fusion. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 4: 21-29. https://doi.org/10.25236/AJCIS.2021.040404.

[1] Sun Min, Li Yang, et al. Sentiment analysis based on CNN-LSTM movie reviews[J]. Journal of Luoyang Institute of Technology (Natural Science Edition), 2019, 4(29): 71-77.

[2] Cheng Yan, Yao Leibo, et al. Multi-channel CNN and BiGRU based on attention mechanism text sentiment tendency analysis[J]. Computer Research and Development, 2020, 57(12): 2583-2592.

[3] Liang Zhang, Yuanfeng Yang, et al. Design and Implementation of Bi-LSTM+Attention Sentiment Analysis Model[J]. Database Technology, 2018: 177-179.

[4] MD Devika, etl. Sentiment Analysis: A Comparative Study On Different Approaches[ J]. Procedia Computer Science, 2016, 87:44-49.

[5] Arnab Hara, etl. A Comparative Study of Different Classifcation Techniques for Sentiment Analysis. International Journal of Synthetic Emotions, 2020,11(1):49-57.

[6] Zeeshan Shaukat,etl. Sentiment analysis on IMDB using lexicon and neural networks. SN Applied Sciences,2020,2(148).

[7] Doaa Mohey,etl. A survey on sentiment analysis challenges[J]. Engineering Sciences,30:330-338.

[8] Chen Zhuang,etl. Transfer Capsule Network for Aspect Level Sentiment Classification. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistic,547-556.

[9] Fang Biyun. Network movie data analysis based on Keras framework [J].Computer Knowledge and Technology, 2019, 15(34):14-16.

[10] Wang Liya, et al. Text sentiment analysis based on CNN-BiLSTM network introducing attention model. Journal of Wuhan Institute of Technology, 2019, 41(4):386-391.

[11] Lin Shiping, et al. Text sentiment analysis combined with knowledge graphs. Journal of Fuzhou University (Natural Science Edition), 2020, 48(3): 270-275.

[12] Li Songru, et al. Sentiment analysis using recurrent neural network attention Force Model. Journal of Huaqiao University (Natural Science Edition), 2018, 39(2):252-255.

[13] Fan Bo, et al. Optimization and improvement of text sentiment analysis technology based on neural network. Electronic technology and software engineering, 180-182.

[14] Qu Zhaowei, etl. Hierarchical attention network sentiment analysis algorithm based on transfer learning. Computer Applications, 2018, 38(11):3053-3056.

[15] Anwar Ur Rehman, etl. A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis. Multimedia Tools and Applocations, 2019.

[16] H.M.Keerthi Kumar, etl. Sentiment Analysis on IMDb Movie Reviews Using Hybrid Feature Extraction Method. Regular Issue, 2019, 109-114.

[17] Chen Tao, etl. Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN. Expert Systems with Applications, 2017, 221-230.

[18] B. Pang, etl. Thumbs up: sentiment classification using machine learning techniques, in: Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, Association for Computational Linguistics, 2002, 79–86.

[19] R. Socher, etl. Recursive deep models for semantic compositionality over a sentiment treebank, in: Proceedings of the conference on empirical methods in natural language processing (EMNLP), 2013, 1631-1642.

[20] H. Yu, etl. Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences, in: Proceedings of the 2003 conference on Empirical methods in natural language processing, Association for Computational Linguistics, 2003, 129–136.

[21] P. Melville, etl. Sentiment analysis of blogs by combining lexical knowledge with text classification, in: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2009,1275–1284.

[22] P.D. Turney, Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews, in: Proceedings of the 40th annual meeting on association for computational linguistics, Association for Computational Linguistics, 2002, 417–424.

[23] X. Hu, etl. Unsupervised sentiment analysis with emotional signals, in: Proceedings of the 22nd international conference on World Wide Web, International World Wide Web Conferences Steering Committee, 2013, 607–618.

[24] A. Gangemi, etl. Frame-based detection of opinion holders and topics: a model and a tool, Comput. Intell. Mag. IEEE, 2014, 9 (1):20–30.