No Access

Sentiment Analysis of Chinese Reviews Based on BiTCN-Attention Model

Jiajing Zhang

https://orcid.org/0000-0002-4802-0356

School of Electronics and Information Engineering, Anhui Jianzhu University, Hefei 230601, China

Search for more papers by this author

Tingting Zhang

School of Electronics and Information Engineering, Anhui Jianzhu University, Hefei 230601, China

Search for more papers by this author

, and

Jinlan Chen

https://orcid.org/0000-0002-5693-2195

School of Mechanical and Electrical Engineering, Anhui Jianzhu University, Hefei 230601, China

E-mail Address: jlchen@163.com

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0129054122420138Cited by:5 (Source: Crossref)

This article is part of the issue:

Special Issue: Mathematical Aspects of Evolutionary Computation and its Applications
Guest Editors: Jia-Bao Liu, Muhammad Javaid and Mohammad Reza Farahani

Abstract

It is of great significance for individuals, enterprises, and government departments to analyze and excavate the sentiment in the comments. Many deep learning models are used for text sentiment analysis, and the BiTCN model has good efficacy on sentiment analysis. However, in the actual semantic expression, the contribution of each word to the sentiment tendency is different, BiTCN treats it fairly and does not pay more attention to the key sentiment words. For this problem, a sentiment analysis model based on the BiTCN-Attention is proposed in this paper. The Self-Attention mechanism and Multi-Head Self-Attention mechanism are added to BiTCN respectively to form BiTCN-SA and BiTCN-MHSA, which improve the weight of sentiment words and the accuracy of feature extraction, to increase the effect of sentiment analysis. The experimental results show that the model accuracies of BiTCN-SA and BiTCN-MHSA in the JingDong commodity review data set are 3.96% and 2.41% higher than that of BiTCN, respectively. In the comment data set of DianPing, the accuracy of BiTCN-SA and BiTCN-MHSA improved by 4.62% and 3.49%, respectively, compared with that of BiTCN.

Communicated by Jia-Bao Liu

Keywords:

References

1. Ji Chen, Ye Huiwen, Wang Zimin, Zhang Xiuwen, Zhao Zihan and Yang Yudong, Social text sentiment analysis based on BiLSTM-CapsNet, Journal of Nanjing University of Science and Technology 46(02) (2022) 205–210, https://doi.org/10.14177/j.cnki.32-1397n.2022.46.02.012. Google Scholar
2. Jia Xibin, Zeng Meng, Mi Qing and Hu Yongli, Domain alignment adversarial unsupervised cross-domain text sentiment analysis algorithm, Journal of Computer Research and Development 59(06) (2022) 1255–1270. Google Scholar
3. W. L. Jiang, K. N. Zhou, C. C. Xiong, G. D. Du, C. B. Ou and J. P. Zhang, KSCB: A novel unsupervised method for text sentiment analysis, Applied Intelligence (2022), https://doi.org/10.1007/s10489-022-03389-4. Crossref, Web of Science, Google Scholar
4. Y. Kim, Convolutional neural networks for sentence classification, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 1746–1751. Google Scholar
5. V. Makarenko, Utilizing recursive neural networks for contextual text analysis, Beer-Sheva:Ben-Gurion University (2019). Google Scholar
6. S. Bai, J. Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, 6th International Conference on Learning Representations, Vancouver, Canada (2018). Google Scholar
7. Y. Zhang and B. Wallace, A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification, in Proceedings of the 8th International Joint Conference on Natural Language Processing, Taipei, Taiwan, (2017) 253–263. Google Scholar
8. J. L. Elman, Finding structure in time, Cognitive Science 14(2) (1990) 179–211. Crossref, Web of Science, Google Scholar
9. K. S. Tai, R. Socher and C. D. Manning, Improved semantic representations from tree-structured long short-term memory networks, Computer Science 5(1) (2015) 36. Google Scholar
10. K. Cho, B. V. Merrienboer, C. Gulcehre et al., Learning Phrase representations using RNN encoder-decoder for statistical machine translation, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, (2014) 1724–1734. Crossref, Google Scholar
11. Nan Deng and BenGong Yu, Sentiment orientation analysis of review text based on sentiment word embedding and BLSTM, Application Research of Computers 35(12) (2018) 3547–3550. Google Scholar
12. JianSheng Han, Chinese text sentiment classification based on bidirectional temporal deep convolution network, Computer Applications and Software 36(12) (2019) 225–231. Google Scholar
13. D. Bahdanau, K. Cho and Y. Bengio, Neural machine translation by jointly learning to align and translate, Computer Science (2014). Google Scholar
14. D. Tang, B. Qin and T. Liu, Aspect level sentiment classification with deep memory network, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, USA (2016). Crossref, Google Scholar
15. Y. Wang, M. Huang, X. Zhu et al., Attention-based LSTM for aspect-level sentiment classification, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, USA (2016). Crossref, Google Scholar
16. A. Vaswani, N. Shazeer, N. Parmar et al., Attention is all you need, 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA, (2017) 5998–6008. Google Scholar
17. J. Zheng, X. Chen, Y. Du et al., Short text sentiment analysis of micro-blog based on bert, Advanced Multimedia and Ubiquitous Engineering, Springer, Singapore (2019) 390–396 Google Scholar
18. R. Cai, B. Qin, Y. Chen et al., Sentiment analysis about investors and consumers in energy market based on BERT-BiLSTM, IEEE Access 8 (2020) 171408–171415. Crossref, Web of Science, Google Scholar
19. H. Ge, S. Zheng and Q. Wang, Based BERT-BiLSTM-ATT model of commodity commentary on The emotional tendency analysis, IEEE 4th International Conference on Big Data and Artificial Intelligence, Sanya, China (2021) 130–133. Crossref, Google Scholar
20. J. Long, E. Shelhamer and T. Darrell, Fully convolutional networks for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence 39(4) (2015) 640–651. Web of Science, Google Scholar
21. Salimans, Tim, Kingma et al., Weight normalization: A simple reparameterization to accelerate training of deep neural networks, Advances in Neural Information Processing Systems, Vol. 29, Barcelona, Spain (2016). Google Scholar
22. V. Nair and G. E. Hinton, Rectified linear units improve restricted boltzmann machines, International Conference on International Conference on Machine Learning, Omnipress (2010). Google Scholar