ABOUT ONE WAY TO ANALYZE THE SENTIMENT OF TEXTS USING ARTIFICIAL NEURAL NETWORKS

  • E. Ivokhin
  • М. Маkhno
  • V. Rets
Keywords: ext sentiment analysis, artificial neural networks, classifiers, bidirectional model, operation algorithm

Abstract

The article discusses in detail the theoretical information of the main approach to tone analysis of the text, conducted research on the topic of automating this process using machine learning and the use of artificial neural networks. The main type of architecture of neural networks for working with text classification is analyzed and the optimal configuration for the implementation of data sentiment analysis is determined. It is concluded that among the possible configurations of artificial neural network models, networks with bidirectional LSTM layers in the form of a GRU configuration perform their function better. At the same time, the accuracy of the results directly depends on the available data sets. The results of comparing the accuracy of training results on the selected datasets are presented. The structure of the software implementation of the configured ANN model is described. An example of its application is given.

Downloads

Download data is not yet available.

References

1. Cambria, Erik, et al. A practical guide to sentiment analysis. – 2017.
2. Ortony, Andrew, Gerald L. Clore, and Allan Collins. The cognitive structure of emotions. Cambridge university press, 1990.
3. Cambria, Erik, Daniel Olsher, and Dheeraj Rajagopal. SenticNet 3: a common and common-sense knowledge base for cognition- driven sentiment analysis// Twenty-eighth AAAI conference on artificial intelligence, 2014.
4. Swapna Somasundaran, Janyce Wiebe, and Josef Ruppenhofer. Discourse level opinion interpretation. In Proc. of the 22nd Int. Conf. on Comp. Linguistics, 2008. Vol.1 (COLING '08). Association for Computational Linguistics, USA, 801–808.
5. S. Poria, E. Cambria, A. Gelbukh, F. Bisio, A. Hussain. Sentiment data flow analysis by means of dynamic linguistic patterns, IEEE Comput. Intell. Mag. 10 (4). – 2013.
6. R.Y. Lan, Y. Xia, Y. Ye. A probabilistic generative model for mining cybercriminal networks from online social media, IEEE Comput. lntell. Mag. 9 (4). – 2014. – Рр. 31—43.
7. Chesley, Paula, et al. Using verbs and adjectives to automatically classify blog sentiment// Training 580.263 (2006): 233.
8. Zhu, Xiaodan, Parinaz Sobihani, and Hongyu Guo. Long short-term memory over recursive structures// Proc. International Conference on Machine Learning. PMLR, 2015.
9. Alex Graves, Jürgen Schmidhuber. Framewise phoneme classification with bidirectional LSTM and other neural network architectures// Neural Networks, 2005. – Vol. 18. – Iss.5–6.
10. Izard, Carroll E. The substrates and functions of emotion feelings: William James and current emotion theory// Personality and Social Psychology Bulletin 16.4 (1990): 626-635.
11. Ekman, Paul. "Emotions revealed." Bmj 328.Suppl S5 (2004).
12. Yao, Kaisheng, et al. Depth-gated recurrent neural networks// arXiv:1508.03790 9 (2015).
13. IMDb Datasets [Online] – Available from: https://www.imdb.com/interfaces/
14. Luong, Minh-Thang, Richard Socher, and Christopher D. Manning. Better word representations with recursive neural networks for morphology// Proceedings of the seventeenth conference on computational natural language learning. 2013.
15. English word vectors[Online] – Available from: https://fasttext.cc/docs/en/english-vectors.html
16. Ian Miell, Aidan Hobson Sayers. Docker in Practice. - Manning Publications. – 2019.
Published
2022-10-03
How to Cite
Ivokhin E. About one way to analyze the sentiment of texts using artificial neural networks / E. Ivokhin, МаkhnoМ., V. Rets // Control, Navigation and Communication Systems. Academic Journal. – Poltava: PNTU, 2022. – VOL. 3 (69). – PP. 71-74. – doi:https://doi.org/10.26906/SUNZ.2022.3.071.