Advertisement

Power Micro-Blog Text Classification Based on Domain Dictionary and LSTM-RNN

  • Meng-yao Shen
  • Jing-sheng Lei
  • Fei-ye Du
  • Zhong-qin BiEmail author
Conference paper
  • 49 Downloads
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 309)

Abstract

The micro-blog texts of the national grid provinces and cities will be analyzed as the main data, including the micro-blogs and corresponding comments, which will help us understand the events of power industry and people’s attitudes towards these events. In this work, the data set is composed of 420,000 micro-blog texts. Firstly, the professional vocabulary of electric power is extracted, and these vocabulary are manually labeled, thus proposing a new field dictionary closely related to the power industry. Secondly, using the new power domain dictionary to classify the 2018 electric micro-blogs, and we can find that classification accuracy increased from 88.7% to 95.2%. Finally, a classification model based on LSTM (Long Short-Term Memory) and RNN (Recurrent Neural Network) is used to deal with the comments under the micro-blog. The experimental result shows that the classification of the LSTM-RNN is more accurate. The rate was 83.1%, which was significantly better than the traditional LSTM and RNN text classification models of 78.4% and 73.1%.

Keywords

Text classification Power micro-blog Domain dictionary Word vector Classification accuracy LSTM-RNN 

References

  1. 1.
    Ding, Y., Jia, Y., Zhou, B.: Survey of data mining for Microblogs. J. Comput. Res. Dev. 51(4), 691–706 (2014)Google Scholar
  2. 2.
    Hou, M., Teng, Y., Li, X., et al.: Research on the language characteristics and emotional analysis strategies of topic-based weibo. Lang. Charact. Appl. 2, 135–143 (2013)Google Scholar
  3. 3.
    Song, S., Li, Q., Lu, D.: A sentiment analysis method for hot events in microblogging. Comput. Sci. 6A, 226–228 (2012)Google Scholar
  4. 4.
    Zhang, Y., Zheng, J., Huang, G., et al.: Microblog sentiment analysis method based on a double attention model. J. Tsinghua Univ. 58(2), 122–130 (2018)Google Scholar
  5. 5.
    Qing, F., Wang, H.C.X., Wang, X.: Microblog sentiment analysis based on linguistic context. Comput. Eng. 43(3), 241–252 (2017)Google Scholar
  6. 6.
    Ning, H., Yang, S., Zhao, Y., et al.: Study of microblog sentiment analysis based on semantic feature. Appl. Sci. Technol. 43(3), 70–74 (2016)Google Scholar
  7. 7.
    Xie, L., Zhou, M., Sun, M.: Hierarchical structure based hybrid approach to sentiment analysis of Chinese micro blog and its feature extraction. J. Chin. Inf. Proc. 26(1), 73–84 (2012)Google Scholar
  8. 8.
    Kombrink, S., Mikolov, T., Karafiát, M., et al.: Recurrent neural network based language modeling in meeting recognition. In: Proceedings of the 12th Annual Conference of the International Speech Communication Association, Florence, Italy, pp. 2877–2880 (2011)Google Scholar
  9. 9.
    Mikolov, T., Kombrink, S., Burget, L., et al.: Extensions of recurrent neural network language model. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, pp. 5528–5531 (2011)Google Scholar
  10. 10.
    Shi, Y.Z., Zhang, W.Q., Liu, J., et al.: RNN language model with word clustering and class-based output layer. EURASIP J. Audio Speech Music Process. 2013, 22 (2013)CrossRefGoogle Scholar
  11. 11.
    Zhao, M., Du, H., Dong, C., et al.: Dietary health text classification based on word2vec and LSTM. Agric. Mach. 48(10), 202–208 (2017)Google Scholar
  12. 12.
    Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078 (2015)
  13. 13.
    Ballesteros, M., Dyer, C., Smith, N.A.: Improved transition-based parsing by modeling characters instead of words with lstms. Comput. Sci. 8(9), e74515 (2015)Google Scholar
  14. 14.
    Socher, R., Lin, C.Y., Ng, A.Y., et al.: Parsing natural scenes and natural language with recursive neural networks. In: Jonny, P., Rob, B. (eds.) International Conference on International Conference on Machine Learning, pp. 129–136. Omni Press, Haifa (2011)Google Scholar
  15. 15.
    Irsoy, O., Cardie, C.: Deep recursive neural networks for compositionality in language. Adv. Neural. Inf. Process. Syst. 3(5), 2096–2104 (2014)Google Scholar
  16. 16.
    Hochreiter, S., Bengio, Y., Frasconi, P., et al.: Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-Term Dependencies, pp. 237–243. Wiley/IEEE Press (2001)Google Scholar
  17. 17.
    Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: Sanjoy, D.D. (ed.) Proceedings of the 30th International Conference on Machine Learning, vol. 28, pp. 1310–1318. JMLR Org, Atlanta (2013)Google Scholar
  18. 18.
    Arisoy, E., Sethy, A., Ramabhadran, B., et al.: Bidirectional recurrent neural network language models for automatic speech recognition. In: Proceedings of the 2015 Annual Conference of International Speech Communication Association, pp. 5421–5425 (2015)Google Scholar
  19. 19.
    Liang, J., Chai, Y., Yuan, H., et al.: Emotional analysis based on polarity transfer and LSTM recursive network. J. Chin. Inf. Sci. 29(5), 152–159 (2015)Google Scholar
  20. 20.
    Liu, P., Qiu, X., Chen, X., et al.: Multrtimescale long short-term memory neural network for modelling sentences and documents. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 2326–2335 (2015)Google Scholar
  21. 21.
    Wang, X., Liu, Y., Sun, C., et al.: Predicting polarities of tweets by composing word embeddings with long short-term memory. In: Proceedings of Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural language Processing, pp. 1343–1353 (2015)Google Scholar
  22. 22.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 20th NIPS, pp. 3104–3112 (2014)Google Scholar
  23. 23.
    Liu, W., Su, Y., Wu, N., et al.: Research on mongolian-chinese machine translation based on LSTM. Comput. Eng. Sci. 40(10), 1890–1896 (2018)Google Scholar
  24. 24.
    Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Proceedings of IEEE International Conference on Acoustics, vol. 38, pp. 6645–6649 (2013)Google Scholar
  25. 25.
    Wang, D., Nyberg, E.: A long short-term memory model for answer sentence selection in question answering. In: Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp. 707–712 (2015)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020

Authors and Affiliations

  • Meng-yao Shen
    • 1
  • Jing-sheng Lei
    • 1
  • Fei-ye Du
    • 1
  • Zhong-qin Bi
    • 1
    Email author
  1. 1.College of Computer Science and TechnologyShanghai University of Electric PowerShanghaiChina

Personalised recommendations