Short Text Aspect-Based Sentiment Analysis Based on CNN + BiGRU
Source abstract
Abstract
This paper describes the construction a short-text aspect-based sentiment analysis method based on Convolutional Neural Network (CNN) and Bidirectional Gating Recurrent Unit (BiGRU). The hybrid model can fully extract text features, solve the problem of long-distance dependence on the sequence, and improve the reliability of training. This article reports empirical research conducted on the basis of literature research. The first step was to obtain the dataset and perform preprocessing, after which scikit-learn was used to perform TF-IDF calculations to obtain the feature word vector weight, obtain the aspect-level feature ontology words of the evaluated text, and manually mark the ontology of the reviewed text and the corresponding sentiment analysis polarity. In the sentiment analysis section, a hybrid model based on CNN and BiGRU (CNN + BiGRU) was constructed, which uses corpus sentences and feature words as the vector input and predicts the emotional polarity. The experimental results prove that the classification accuracy of the improved CNN + BiGRU model was improved by 12.12%, 8.37%, and 4.46% compared with the Convolutional Neural Network model (CNN), Long-Short Term Memory model (LSTM), and Convolutional Neural Network (C-LSTM) model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques · Text and Document Classification Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Economics and Management, South China Normal University, Guangzhou 510006, China
Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China
References (36)
Show source-provided references
1. Reducing the Dimensionality of Data with Neural Networks10.1126/science.1127647 ↗
2. Character-Level Convolutional Networks for Text Classification
3. Review of Advances in Neural Networks: Neural Design Technology Stack10.1016/j.neucom.2015.02.092 ↗
4. Xu, G. (2021). Face Recognition Research Based on Convolutional Neural Network. [Master’s Thesis, Harbin University of Science and Technology].
5. Zhang, C. (2020). The Research of Bone Age Assessment Method Based on Convolutional Neural Networks and Multi-scale Feature Fusion. [Master’s Thesis, Hefei University of Technology].
6. Cross-Modal Hashing Retrieval Based on Deep Residual Network10.32604/csse.2021.014563 ↗
7. Irie, K., Tüske, Z., Alkhouli, T., Schlüter, R., and Ney, H. (2016, January 8–12). Lstm, Gru, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition. Proceedings of the 17th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2016), San Francisco, CA, USA.10.21437/Interspeech.2016-491 ↗
8. Cui, Y. (2020). Research on Sentiment Analysis of Product Reviews Based on Dual-channel Mixed Neural Network. [Master’s Thesis, Xinyang Normal University].
9. Chinese text sentiment analysis based on CNN-BiGRU network with attention mechanism
10. Text sentiment classification model based on BiGRU-attention neural network
11. Prediction of COVID-19 epidemic based on BiGRU-Attention network
12. Feng, X., and Liu, X. (2019, January 22–24). Sentiment Classification of Reviews Based on BiGRU Neural Network and Fine-Grained Attention. Proceedings of the 3rd International Conference on Machine Vision and Information Technology (CMVIT), Guangzhou, China.
13. Construction and Analysis of Emotion Computing Model Based on LSTM10.1155/2021/8897105 ↗
14. A Textual Sentiment Analysis Model Based on Multi-Hop Reasoning
15. Sentence-Level Sentiment-Based Sentiment Polarity Classification of Chinese Online Reviews
16. Yan, W. (2021). Research on Text Sentiment Analysis Based on Deep Learning. [Master’s Thesis, Harbin University of Science and Technology].
17. Paltoglou, G., and Thelwall, M. (2010, January 11–16). A Study of Information Retrieval Weighting Schemes for Sentiment Analysis. Proceedings of the 48th Annual Meeting of the Association-for-Computational-Linguistics (ACL), Uppsala, Sweden.
18. Faruqui, M., Dodge, J., Jauhar, S.K., Dyer, C., Hovy, E., and Smith, N.A. (2014). Retrofitting word vectors to semantic lexicons. arXiv.10.3115/v1/N15-1184 ↗
19. Incremental Word Vectors for Time-Evolving Sentiment Lexicon Induction
20. Yang, J. (2019). Research on Fine-grained Sentiment Analysis for Text. [Doctoral Thesis, Nanjing University].
21. Thinh, N.K., Nga, C.H., Lee, Y.S., Wu, M.L., Chang, P.C., and Wang, J.C. (2019, January 9–11). Sentiment Analysis Using Residual Learning with Simplified Cnn Extractor. Proceedings of the 21st IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA.10.1109/ISM46123.2019.00075 ↗
22. Zhang, S. (2021). Research on Key Issues of Chinese Short Text Sentiment Analysis. [Master’s Thesis, Northwest University].
23. Tran, T.U., Hoang, H.T.T., and Huynh, H.X. (2019, January 20–22). Aspect Extraction with Bidirectional GRU and CRF. Proceedings of the IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF), Danang, Vietnam.10.1109/RIVF.2019.8713663 ↗
24. Han, Y. (2021). Research on BiGRU based Aspect-level Sentiment Classification Method for Drug Reviews. [Master’s Thesis, Northeast Forestry University].
25. Sentiment classification method based on BiGRU and aspect attention module
26. Multi-perspectives systematic review on the applications of sentiment analysis for vaccine hesitancy10.1016/j.compbiomed.2021.104957 ↗
27. Social media sentiment analysis through parallel dilated convolutional neural network for smart city applications10.1016/j.comcom.2020.02.044 ↗
28. Text sentiment orientation analysis of multi-channels CNN and BIGRU based on attention mechanism
29. Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods10.1016/j.rinp.2021.104495 ↗
30. Chinese Ship Fault Relation Extraction Method Based on Bidirectional GRU Neural Network and Attention Mechanism
31. Text Sentiment Analysis Capsule Model Combining Convolutional Neural Network and Bidirectional GRU
32. Aspect-based sentiment analysis based on graph neural network
33. Aspect level sentiment analysis based on distance and graph convolution network
34. Textual Backdoor Attack for the Text Classification System10.1155/2021/2938386 ↗
35. Rolling bearing fault mode recognition based on 2D image and CNN-BiGRU
36. Mohammad, A.S., Hammad, M.M., Sa’ad, A., Saja, A.T., and Cambria, E. (2021). Gated Recurrent Unit with Multilingual Universal Sentence Encoder for Arabic Aspect-Based Sentiment Analysis. Knowl. -Based Syst., 107540.