Cross-Domain Text Sentiment Classification Method Based on the CNN-BiLSTM-TE Model = Cross-Domain Text Sentiment Classification Method Based on the CNN-BiLSTM-TE Model

다국어 초록 (Multilingual Abstract)

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model’s F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

참고문헌 (Reference)

1 G. A. Miller, "WordNet : a lexical database for English" 38 (38): 39-41, 1995

2 J. Lu, "Transfer learning using computational intelligence : a survey" 80 : 14-23, 2015

3 B. Pang, "Thumbs up? Sentiment classification using machine learning techniques" 79-86, 2002

4 H. Zhao, "Text sentiment analysis based on serial hybrid model of bi-directional long short-term memory and convolutional neural network" 40 (40): 16-20, 2020

5 Y. Zhang, "Study of sentiment classification for Chinese microblog based on recurrent neural network" 25 (25): 601-607, 2016

6 J. Li, "Research on product feature extraction and sentiment classification of short online review based on deep learning" 41 (41): 143-148, 2018

7 J. Liang, "Polarity shifting and LSTM based recursive networks for sentiment analysis" 29 (29): 152-159, 2015

8 S. F. Zeng, "New method of text representation model based on neural network" 38 (38): 86-98, 2017

9 L. W. Ku, "Mining opinions from the web : beyond relevance retrieval" 58 (58): 1838-1850, 2007

10 S. Hochreiter, "Long short-term memory" 9 (9): 1735-1780, 1997

11 J. Qiu, "Leveraging sentiment analysis at the aspects level to predict ratings of reviews" 451 : 295-309, 2018

12 G. E. Hinton, "Learning distributed representations of concepts" 1986

13 G. E. Hinton, "Improving neural networks by preventing co-adaption of feature detectors"

14 A. Graves, "Hybrid speech recognition with deep bidirectional LSTM" 273-278, 2013

15 J. F. Xu, "Hybrid algorithm framework for sentiment classification of chinese based on semantic comprehension and machine learning" 42 (42): 61-66, 2015

16 P. D. Turney, "From frequency to meaning : vector space models of semantics" 37 : 141-188, 2010

17 T. Mikolov, "Efficient estimation of word representations in vector space"

18 Y. Kim, "Convolutional neural networks for sentence classification" 1746-1751, 2014

19 X. D. Guo, "Consumer reviews sentiment analysis based on CNN-BiLSTM" 40 : 653-663, 2020

20 A. Joshi, "C-Feel-It: a sentiment analyzer for microblogs" 127-132, 2011

21 S. P. Zhai, "Bilingual text sentiment analysis based on attention mechanism Bi-LSTM" 36 (36): 251-255, 2019

22 S. Tan, "An empirical study of sentiment analysis for Chinese documents" 34 (34): 2622-2629, 2008

23 H. Tang, "A survey on sentiment detection of reviews" 36 (36): 10760-10773, 2009

24 Y. Bengio, "A neural probabilistic language model" 3 : 1137-1155, 2003

25 E. Boiy, "A machine learning approach to sentiment analysis in multilingual web texts" 12 (12): 526-558, 2009

26 Y. X. He, "A deep learning model enhanced with emotion semantics for microblog sentiment analysis" 40 (40): 773-790, 2017

27 N. Kalchbrenner, "A convolutional neural network for modelling sentences" 655-665, 2014