Research on Chinese Microblog Sentiment Classification Based on TextCNN-BiLSTM Model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speechand emoticons without comprehending users’ emotional inclinations and grasping moral nuances. This studyproposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the modelemploys 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 isutilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments arecategorized using a classification layer. Given the binary classification task at the output layer and the numeroushidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findingsdemonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to theindividual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9%in precision, recall, and F1 values.
Abstract
Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speechand emoticons without comprehending users’ emotional inclinations and grasping moral nuances. This studyproposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the modelemploys 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 isutilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments arecategorized using a classification layer. Given the binary classification task at the output layer and the numeroushidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findingsdemonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to theindividual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9%in precision, recall, and F1 values.
참고문헌 (28)
- R. Zeng, "A study on early warning mechanism and index for network opinion", Journal of Information, 28(11), pp.52~54 (2009)
- R. Li, "Text emotion analysis: a survey", Journal of Computer Research and Development, 55(1), pp.30~52 (2018)[DOI]
- J. Wu, "Sentiment analysis of film review based on multiple sentiment dictionary and SVM", Journal of Fuyang Normal University (Natural Science edition), 36(2), pp.68~72 (2019)
- Z. Cheng, "Sentiment analysis method of online comments based on support vector machine", Electronic Technology & Software Engineering, 2019(16), pp.3~4 (2019)
- W. J. Cui, "Deep learning-based text emotion analysis", Ph.D., pp.2018
- L. Dang, "Method of discriminant for Chinese sentence sentiment orientation based on HowNet", Application Research of Computers, 27(4), pp.1370~1372 (2010)
- K. Wang, "A survey on automatical construction methods of sentiment lexicons", Acta Automatica Sinica, 42(4), pp.495~511 (2016)[DOI]
- Y. M. Zhou, "A method on building Chinese sentiment lexicon for text sentiment analysis", Journal of Shandong University (Engineering Science), 43(6), pp.27~33 (2013)
- Y. Zhao, "Large-scale sentiment lexicon collection and its application in sentiment classification", Journal of Chinese Information Science, 31(2), pp.187~193 (2017)
- C. Jiang, "Constructing a domain sentiment lexicon based on Chinese social media text", Data analysis and Knowledge Discovery, 3(2), pp.98~107 (2019)[DOI]
- B. Pang, "Thumbs up? Sentiment classification using machine learning techniques", Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.78~86 (2002)
- Jun Li, "Multi-label maximum entropy model for social emotion classification over short text", Neurocomputing, 210, pp.247~256 (2016), Elsevier BV[DOI]
- S. Kaur, "Sentiment analysis approach based on N-gram and KNN classifier", Proceedings of 2018 1st International Conference on Secure Cyber Computing and Communication (ICSCCC), pp.1~4 (2018)
- L. Zhang, "Analyzing the features of negative sentiment microblog", Intelligence Theory and Practice, 42(7), pp.132~137 (2019)[DOI]
- M. Sun, "Sentiment analysis based on BGRU and self-attention mechanism", Journal of Jianghan University(Natural Science Edition), 48(4), pp.80~89 (2020)[DOI]
- H. Zhao, "Text sentiment analysis based on serial hybrid model of bi-directional long short-term memory and convolutional neural network", Journal of Computer Applications, 40(1), pp.16~22 (2020)[DOI]
- Y. Miao, "Application of CNN-BiGRU model in Chinese short text sentiment analysis", Information Science, 39(4), pp.85~91 (2021)
- Q. Yang, "Text sentiment analysis based on fusion of attention mechanism and BiGRU", Computer Science, 48(11), pp.307~311 (2021)[DOI]
- L. Yan, "Emotional classification algorithm of comment text based on two-channel fusion and BiLSTM-attention", Journal of University of Shanghai for Science and Technology, 43(6), pp.597~605 (2021)[DOI]
- H. Fan, "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, 39(4), pp.15~22 (2021)[DOI]
- X. Yang, "Improved BiLSTM-CNN+Attention sentiment classification algorithm fused with sentiment dictionary", Science Technology and Engineering, 22(20), pp.8761~8770 (2022)
- B. Shen, "Microblog sentiment analysis based on ERNIE and dual attention mechanism", Journal of Yunnan University (Natural Science Edition), 44(3), pp.480~489 (2022)[DOI]
- M. H. Ali Al-Abyadh, "Deep sentiment analysis of twitter data using a hybrid ghost convolution neural network Model", Computational Intelligence and Neuroscience, 2022 (2022)
- Y. Hu, "Self-attention-based BGRU and CNN for sentiment analysis", Computer Science, 49(1), pp.252~258 (2022)[DOI]
- Lal Khan, "Multi-class sentiment analysis of urdu text using multilingual BERT", Scientific Reports, 12(1) (2022), Springer Science and Business Media LLC[DOI]
- O. Wu, "Two-level LSTM for sentiment analysis with lexicon embedding and polar flipping", IEEE Transactions on Cybernetics, 52(5), pp.3867~3879 (2022)[DOI]
- Y. Lecun, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86(11), pp.2278~2324 (1998), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Sepp Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997), MIT Press - Journals[DOI]