Journal of Information Processing Systems

  • 제19권6호
  • /
  • Pages.842-857
  • /
  • 2023
  • /
  • 1976-913X(pISSN)
  • /
  • 2092-805X(eISSN)
한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

Research on Chinese Microblog Sentiment Classification Based on TextCNN-BiLSTM Model

  • Haiqin Tang (School of Business and Tourism, Sichuan Agricultural University) ;
  • Ruirui Zhang (School of Business and Tourism, Sichuan Agricultural University)
  • 투고 : 2022.04.28
  • 심사 : 2022.12.11
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

키워드

참고문헌

  1. R. Zeng and X. Xu, "A study on early warning mechanism and index for network opinion," Journal of Information, vol. 28, no. 11, pp. 52-54, 2009.
  2. R. Li, Z. Lin, H. Lin, W. Wang, and D. Meng, "Text emotion analysis: a survey," Journal of Computer Research and Development, vol. 55, no. 1, pp. 30-52, 2018. https://doi.org/10.7544/issn1000-1239.2018.20170055
  3. J. Wu, K. Lu, and S. B. Wang, "Sentiment analysis of film review based on multiple sentiment dictionary and SVM," Journal of Fuyang Normal University (Natural Science edition), vol. 36, no. 2, pp. 68-72, 2019.
  4. Z. Cheng and L. Wang, "Sentiment analysis method of online comments based on support vector machine," Electronic Technology & Software Engineering, vol. 2019, no. 16, pp. 3-4, 2019.
  5. W. J. Cui, "Deep learning-based text emotion analysis," Ph.D. dissertation, Jilin University, Changchun, China, 2018.
  6. L. Dang and L. Zhang, "Method of discriminant for Chinese sentence sentiment orientation based on HowNet," Application Research of Computers, vol. 27, no. 4, pp. 1370-1372, 2010.
  7. K. Wang and R. Xia, "A survey on automatical construction methods of sentiment lexicons," Acta Automatica Sinica, vol. 42, no. 4, pp. 495-511., 2016 https://doi.org/10.16383/j.aas.2016.c150585
  8. Y. M. Zhou, J. L. Yang, and A. M. Yang, "A method on building Chinese sentiment lexicon for text sentiment analysis," Journal of Shandong University (Engineering Science), vol. 43, no. 6, pp. 27-33, 2013.
  9. Y. Zhao, B. Qin, Q. Shi, and T. Liu, "Large-scale sentiment lexicon collection and its application in sentiment classification," Journal of Chinese Information Science, vol. 31, no. 2, pp. 187-193, 2017.
  10. C. Jiang, Y. Guo, and Y. Liu, "Constructing a domain sentiment lexicon based on Chinese social media text," Data analysis and Knowledge Discovery, vol. 3, no. 2, pp. 98-107, 2019. https://doi.org/10.11925/infotech.2096-3467.2018.0578
  11. B. Pang, L. Lee, and S. Vaithyanathan, "Thumbs up? Sentiment classification using machine learning techniques," in Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), Philadelphia, PA, USA, 2002, pp. 78-86.
  12. J. Li, Y. Rao, F. Jin, H. Chen, and X. Xiang, "Multi-label maximum entropy model for social emotion classification over short text," Neurocomputing, vol. 210, pp. 247-256, 2016. https://doi.org/10.1016/j.neucom.2016.03.088
  13. S. Kaur, G. Sikka, and L. K. Awasthi, "Sentiment analysis approach based on N-gram and KNN classifier," in Proceedings of 2018 1st International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, 2018, pp. 1-4.
  14. L. Zhang, Y. Tan, L. Zhu, and W. Dong, "Analyzing the features of negative sentiment microblog," Intelligence Theory and Practice, vol. 42, no. 7, pp. 132-137, 2019. http://www.itapress.cn/CN/Y2019/V42/I7/132
  15. M. Sun, Y. Li, Z. Zhuang, and T. Qian, "Sentiment analysis based on BGRU and self-attention mechanism," Journal of Jianghan University (Natural Science Edition), vol. 48, no. 4, pp. 80-89, 2020. https://doi.org/10.16389/j.cnki.cn42-1737/n.2020.04.011
  16. H. Zhao, L. Wang, and W. Wang, "Text sentiment analysis based on serial hybrid model of bi-directional long short-term memory and convolutional neural network," Journal of Computer Applications, vol. 40, no. 1, pp. 16-22, 2020. https://doi.org/10.11772/j.issn.1001-9081.2019060968
  17. Y. Miao, Y. Ji, S. Zhang, W. Cheng, and E. Peng, "Application of CNN-BiGRU model in Chinese short text sentiment analysis," Information Science, vol. 39, no. 4, pp. 85-91, 2021.
  18. Q. Yang, Y. Zhang, J. Zhu, and T. Wu, "Text sentiment analysis based on fusion of attention mechanism and BiGRU," Computer Science, vol. 48, no. 11, pp. 307-311, 2021. https://doi.org/10.11896/jsjkx.201000075
  19. L. Yan, X. Zhu, and X. Chen, "Emotional classification algorithm of comment text based on two-channel fusion and BiLSTM-attention," Journal of University of Shanghai for Science and Technology, vol. 43, no. 6, pp. 597-605, 2021. https://doi.org/10.13255/j.cnki.jusst.20210102001
  20. H. Fan and P. F. Li, "Sentiment analysis of short text based on FastText word vector and bidirectional GRU recurrent neural network: take the microblog comment text as an example," Information Science, vol. 39, no. 4, pp. 15-22, 2021. https://lib.cqvip.com/Qikan/Article/Detail?id=7104517819 104517819
  21. X. Yang, M. Guo, H. Hou, J. Yuan, X. Li, K. Li, W. Wang, S. He, and Z. Luo, "Improved BiLSTM-CNN+ Attention sentiment classification algorithm fused with sentiment dictionary," Science Technology and Engineering, vol. 22, no. 20, pp. 8761-8770, 2022. http://www.stae.com.cn/jsygc/article/abstract/2112609?st=alljournals
  22. B. Shen, X. Yan, L. Zhou, G. Xu, and Y. Liu, "Microblog sentiment analysis based on ERNIE and dual attention mechanism," Journal of Yunnan University (Natural Science Edition), vol. 44, no. 3, pp. 480-489, 2022. https://doi.org/10.7540/j.ynu.20210263
  23. M. H. Ali Al-Abyadh, M. A. Iesa, H. A. Hafeez Abdel Azeem, D. P. Singh, P. Kumar, M. Abdulamir, and A. Jalali, "Deep sentiment analysis of twitter data using a hybrid ghost convolution neural network Model," Computational Intelligence and Neuroscience, vol. 2022, article no. 6595799, 2022. https://doi.org/10.1155/2022/6595799
  24. Y. Hu, T. Tong, X. Zhang, and J. Peng, "Self-attention-based BGRU and CNN for sentiment analysis," Computer Science, vol. 49, no. 1, pp. 252-258, 2022. https://doi.org/10.11896/jsjkx.210600063
  25. L. Khan, A. Amjad, N. Ashraf, and H. T. Chang, "Multi-class sentiment analysis of Urdu text using multilingual BERT," Scientific Reports, vol. 12, no. 1, article no. 5436, 2022. https://doi.org/10.1038/s41598-022-09381-9
  26. O. Wu, T. Yang, M. Li, and M. Li, "Two-level LSTM for sentiment analysis with lexicon embedding and polar flipping," IEEE Transactions on Cybernetics, vol. 52, no. 5, pp. 3867-3879, 2022. https://doi.org/10.1109/TCYB.2020.3017378
  27. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. https://doi.org/10.1109/5.726791
  28. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735