Elements of neural networks technology for analyzing the attitude of Twitter users towards brands

Olga Zhulanova, Bachelor

Факультет інформаційних технологій, Київський національний університет імені Faculty of Information Technology, Taras Shevchenko National University of Kyiv, Ukraine

ORCID ID: 0000-0001-6231-0600

Olena Vashchilina, PhD (Phys. & Math.), Assoc. Prof.,

Faculty of Information Technology, Taras Shevchenko National University of Kyiv, Ukraine

ORCID ID: 0000-0001-6867-6216

Abstract

DOI: https://doi.org/10.17721/AIT.2023.1.02

Background. The article is devoted to the issues of effective organization of collection and information analysis about the attitude of Twitter users to brands in the software application form. Issues such as research into modern means of collecting and analyzing information are considered; definition of the functionality that the application should implement; analysis of architectural solutions and selection of software necessary for its implementation.

Methods. When conducting research, marketing theory is used in the field of collecting information about consumer opinions, research on methods of information analysis for the purpose of classifying consumer mood, empirical analysis and synthesis of architectures used in the creation and comparison of neural network models for text classification, development and construction of own model for classification.

Results. As part of the task of software implementation of tweet text analysis, the architecture of convolutional and recurrent neural networks was investigated, a comparison of various hyper parameter values of neural networks was made, in particular, activation functions, loss functions, the number of learning epochs, the number of network layers, a comparison of different Python libraries for processing natural languages in the context of tweet evaluation.

Сonclusions. The practical significance of the study is the creation of a software tool for effective analysis of Twitter users’ attitudes towards brands, which can serve to improve the effectiveness of marketing activities of brands.

Keywords: Twitter, information analysis, text classification, sentiment analysis, neural networks, software application, Python libraries.

Information about the author

Olga Zhulanova, Bachelor, majoring in “Computer Science”, Faculty of Information Technologies, Taras Shevchenko National University of Kyiv.

Research interests: development and training of neural networks for analyzing data and making predictions based on them.

Olena Vashchilina, PhD (Phys. & Math.), Assoc. Prof., Associate Professor of the Department of Applied Information Systems, Faculty of Information Technologies, Taras Shevchenko National University of Kyiv.

Research interests: use of mathematics and information technologies to solve applied problems.

References
PDF

Published

2023-12-15

How to Cite

O. Zhulanova, O. Vashchilina “Elements of neural networks technology for analyzing the attitude of Twitter users towards brands, Advanced Information Technology, vol.1(2), pp.   13–22   , 2023.

Issue

Advanced Information Technology № 1 (2), 2023

Section

Applied information systems and technology

DOI: https://doi.org/10.17721/AIT.2023.1.02

  1. Appel, O., Chiclana, F., Carter, J., & Fujita, H.  (2016). A hybrid approach to the sentiment analysis problem at the sentence level. Knowledge-Based Systems,(108). https://doi.org/10.1016/j.knosys.2016.05.040
  2. Chandra, P., & Singh, Y. (2004). Feedforward Sigmoidal Networks–Equicontinuity and Fault-Tolerance Properties. IEEE Transactions on Neural Networks, 15(6),  1350–1366. https://doi.org/10.1109/tnn.2004.831198
  3. Chiang, Y. M, Chang, L. C, & Chang, F. J.  (2004). Comparison of static-feedforward and dynamic-feedback neural networks for rainfall-runoff modeling. Hydrol. 297–311.
  4. Choi, D., Shallue, C. J., Nado, Z., Lee, J., Maddison, C., J., & Dahl, G. E. (2019). On Empirical Comparisons of Optimizers for Deep Learning. Addis Ababa.
  5. Conneau, A., Schwenk, H., Barrault, L., & Lecun, Y.  (2017). Very Deep Convolutional Networks for Text Classification. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, (1), Long Papers, Valencia, Spain. https://doi.org/10.18653/v1/e17-1104
  6. Farzad, A., Mashayekhi, H., & Hassanpour, H. (2019). A comparative performance analysis of different activation functions in LSTM networks for classification. Springer, 31 (5). (pp.2507–2521). doi:10.1007/s00521-017-3210-6
  7. Higginbotham, J. (2015). Designing Great Web APIs. O’Reilly Media, Inc.
  8. Keras. (2023). Conv1D layer. https://keras.io/api/layers/convolution_layers/convolution1d/
  9. Kingma, D. P., & Ba, J. A. (2014). A Method for Stochastic Optimization. ICLR. https://www.kaggle.com/datasets/ishantjuyal/emotions-in-text. doi.10.48550/arXiv.1412.6980
  10. Kirsch, K. (2023). What Is Brand Perception? How to Measure It and 4 Examples. Hubspot. https://blog.hubspot.com/marketing/what-is-brand-perception. July 05, 2023.
  11. LeRoy Elliott D. (1998). A better Activation Function for Artificial Neural Networks. Technical Research Report, (3).
  12. Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., & Gao, J. (2021). Deep Learning–based Text Classification: A Comprehensive Review.  ACM Computing Surveys, 54(3). (pp. 1–40). doi:10.1145/3439726.
  13. Nistor, S.C., Moca, M., Moldovan, D., Oprean, D. B. & Nistor, R. L. (2021) Building a Twitter Sentiment Analysis System with Recurrent Neural Networks. Sensors. (pp. 1-24). doi.org:10.3390/s21072266.
  14. Ostrovskiy, S. (2021). Twitter – Briefly about the social network of the short format. ApiX-Drive. https://apix-drive.com/ru/blog/useful/twitter-korotko-o-socialnoj-seti-korotkogo-formata [in Ukrainian].
  15. Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training Recurrent Neural Networks. Proceedings of the 30th International Conference on International Conference on Machine Learning, Atlanta GA.
  16. Sheng, T. K., Socher R. D., & Manning C. (2015). Improved Semantic Representations from Tree-Structured Long Short-Term Memory Networks. doi:10.48550/arXiv.1503.00075.
  17. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15(56),1929−1958.
  18. Statista. (2021). Distribution of Twitter users worldwide as of April 2021, by age group. https://www.statista.com/statistics/283119/age-distribution-of-global-twitter-users/.
  19. Zhu X., Sobhani P., & Guo H. (2015). Long Short-Term Memory Over Recursive Structures. Proceedings of Machine Learning Research, (37), 1602–1612.