Chuchun Liu
ABSTRACT
In the classification of emotion analysis, the research results of film review emotion analysis are relatively few. This paper starts with context information. Combining RoBERTA pre-training model and BiLSTM model, we use LSTM, BiLSTM, RoBERta-LSTM, BERT-BiLSTM and RoBERta-BilSTM models to conduct emotional analysis on the IMDB movie data set. The experimental data shows that the adoption of the BiLSTM model is better than LSTM, and RoBERTA is better than BERT. The combination of RoBERTA and BiLSTM has higher accuracy and can be well applied in the emotional analysis of film reviews.
- The 50th Statistical Report on China's Internet Development [EB/OL]. China Internet Information Center, 2022, http://www.cnnic.net.cn/NMediaFile/2022/0926/MAIN1664183425619U2MS433V3V.pdf.Google Scholar
- Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets [J]. Neural computation, 2006, 18(7): 1527-1554.Google Scholar
- Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786): 504-507.Google Scholar
- Hu Xinchen. Research on semantic relationship classification based on LSTM [D]. Harbin: Harbin Institute of Technology, 2015.Google Scholar
- Yang Chunxia, Song Jinjian, Yao Sicheng. Aspect-level emotion analysis based on deep BiLSTM and graph convolution network [J]. Computer Engineering and Science, 2022,44 (10): 1893-1900.Google Scholar
- Chen Ke, Liang Bin, Ke Wende, Emotional analysis of Chinese microblog based on multi-channel convolutional neural network [J]. Computer Research and Development, 2018, 55 (05): 945-957.Google Scholar
- DEVLINJ, CHANGMW, LEEK, BERT: pre-training of deep bidirectional transformers for language under standing [EB/OL]. (2018Oct11), 2018.Google Scholar
- Jacob Devlin, Ming-weiChang, KentonLee, etal. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.arXiv:1801.04805v1 [cs.CL], 2018.Google Scholar
- LIUYH, OTTM, GOYALN, etal. Roberta: Arobustly optimize dbert pretrainin gap proach [EB/OL]. (2019Jul26) 2020, 07-09. https://arxiv.org/pdf/1907.11692.pdfGoogle Scholar
- Yuan Xiaorong, Zhang Dan. Research on emotion classification of microblog users combined with RoBERTA and BiSRU-AT [J]. Microcomputer Application, 2022,38 (10): 6-9Google Scholar
- Qiu Xipeng, Neural Network and Deep Learning, Chapter 6 Cyclic Neural Network, Github Inc., March 12, 2018 [citation date: December 9, 2018]Google Scholar
- Huang Jie. Text emotion analysis based on neural network [D]. Zhejiang University of Technology, 2020. DOI: 10.27463/d.cnki.gzgyu.2020.001549Google Scholar
Recommendations
Comparative analysis of affective and physiological responses to emotional movies
In this research, we investigated on user's affective and physiological responses to the emotional movies. The emotional movies provide continuous feedback such as changes in saturation, brightness and contrast of the movie in response to users' ...
Assessing naturalness and emotional intensity: a perceptual study of animated facial motion
SAP '14: Proceedings of the ACM Symposium on Applied PerceptionAnimated characters appear in applications for entertainment, education, and therapy. When these characters display appropriate emotions for their context, they can be particularly effective. Characters can display emotions by accurately mimicking the ...
Comments