In this paper, we proposed a deep fusion model for telephone comments recognition, named CNN-BiGRU. Traditionally, the most used algorithms in text classification are Convolutional Neural Network (CNN), Long and Short Term Memory (LSTM) and Bi-Gated Recurrent Neural Network (BiGRU). For CNN, it can extract the feature form the neighbors, and a softmax layer is followed for classification. The global feature is not included in the CNN model. LSTM introduces the gate, which can capture the information before the node. BiGRU is developed from LSTM, and it can find the features in the context. So compared to LSTM, BiGRU not only includes the information before, but also can capture the following features. Thus, LSTM and BiGRU can extract the global features, but cannot capture the local features. In order to deal with this weakness, we proposed a fusion model for comments classification, which combines the CNN and BiGRU in our model. Different from other methods, CNN and BiGRU are parallelly connected. CNN model can extract the local feature, and BiGRU can find the global feature. Then we concatenate the two kinds of features and feed to recognition layer for classification. Then we use our model to classify the telephone comments; compared with the traditional machine SVM and tow deep neural models — CNN and BiGRU — our model performed better.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

1. A. Giachanou and F. Crestani, Like It or Not: A Survey of Twitter Sentiment Analysis Methods, ACM Comput. Surveys 49(2) (2016) 1–41. Crossref, Google Scholar
2. E. Boiy and M. F. Moens, A machine learning approach to sentiment analysis in multilingual Web texts, Inform. Retrieval 12(5) (2009) 526–558. Crossref, Google Scholar
3. Y. Chao, F. Shi, W. Daling et al., Analysis of network public opinion tendency based on emotion dictionary expansion technology, Minicomput. Syst. 31(4) (2010) 691–695. Google Scholar
4. X. Faju, L. Chen and T. Li, A survey of online comment emotion analysis, Softw. Guide 17(2) (2018) 1–4. Google Scholar
5. Z. Gang and X. Zan, Research on emotion analysis model of commodity comments based on machine learning, Res. Inform. Security 3(2) (2017) 166–170. Google Scholar
6. N. Qiang, W. Zhixiao and C. Dai, Research on Web Text Classification Based on KNN, Comput. Appl. Softw. 24(10) (2007) 210–211. Google Scholar
7. W. Huiling, Research on the application of text emotion analysis in product review, PhD thesis, Beijing Jiaotong University 2014. Google Scholar
8. Y. Tong, Y. Zhang and Y. Jiang, Study of sentiment classification for Chinese microblog based on recurrent neural networks, Chin. J. Electron. 25(4) (2016) 601–607. Crossref, Google Scholar
9. Z. Chengqing, Statistical Natural Language Processing (Tsinghua University Press, Beijing, 2007). Google Scholar
10. D. Chuanming, Comparative analysis of traditional emotion classification methods and emotion classification methods based on deep learning, Softw. Guide 1 (2018) 22–24. Google Scholar
11. X. Shi, Z. Chen, H. Wang, D. Y. Yeung, W. K. Wong and W. C. Woo, Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting (MIT Press, 2015). Google Scholar
12. X. Wang, Y. Liu, C. Sun et al., Predicting polarities of tweets by composing word embeddings with long short-term memory, Int. Joint Conf. Natural Language Processing (2015), pp. 1343–1353. Crossref, Google Scholar
13. K. Cho, B. V. Merrienboer, C. Gulcehre et al., Learning phrase representations using RNN encoder-decoder for statistical machine translation, Comput. Sci. (2014). Google Scholar
14. Y. Kim, Convolutional neural networks for sentence classification, Minicomput. Syst. (2014) 1746–1751. Google Scholar
15. H. Ren and Z. Wei, Research on emotional tendency of Internet commodity comments based on word2vec, Comput. Sci. 43(1) (2016) 387–389. Google Scholar
16. X. Rong, word2vec parameter learning explained, arXiv:1411.2738 (2014). Google Scholar
17. W. Zhengcheng and L. Dandan, Emotion classification of short text based on word vector and emotion ontology, J. Zhejiang Univ. Technol. (Social Science Edition) 40(1) (2018) 33–38. Google Scholar
18. D. Zhang, H. Xu, Z. Su et al., Chinese comments sentiment classification based on word2vec and SVMperf, Expert Syst. Appl. 42(4) (2015) 1857–1863. Crossref, Google Scholar
19. Z. Dongwen, Y. Pengfei and X. Yunfeng, Research on emotion classification of Chinese comments based on word2vec and SVMperf, Comput. Sci. (2016) S1:5. Google Scholar
20. Y. Bengong and Z. Lianbin, Research on Chinese short text classification based on CP-CNN, Comput. Appl. Res. 35(4) (2018). Google Scholar
21. C. Santos and M. Gattit, Deep convolutional neural networks for sentiment analysis of short texts, Int. Conf. Computational Linguistics (2014). Google Scholar
22. D. Tang, Q. Bing and T. Liu, Document modeling with gated recurrent neural network for sentiment classification, Conf. Empirical Methods in Natural Language Processing (2015). Crossref, Google Scholar