Abstract
The goal of the paper is to create a system for sarcasm recognition in texts. The system effectiveness is significantly better than a random guess and it is functional in chosen types of sarcasm. The system is tested and created using datasets based on input from Twitter users but also on headlines of online news magazines. Used datasets contain different type of sarcasm in form appropriate for neural network to train on. The limitation of the system is recognition of specialized sarcasm which requires a unique knowledge to understand it and consider it to be an instance of sarcasm. The system determines sarcasm only through the website and seek the proper context, so the system determines sarcasm only in the given sentence. Two basic solutions had been developed: a neural network with different configurations of layers and a convolutional neural network. The implemented solutions give very satisfactory results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bouazizi, M., Ohtsuki, T.: A pattern-based approach for sarcasm detection on Twitter. IEEE Access 4(1–1), 5477–5488 (2016)
Chaudhari, P., Chandankhede, C.: Literature Survey of Sarcasm Detection. In: IEEE WiSPNET 2017 Conference, pp. 2041–2046 (2017)
Davidov, D., Tsur, O., Rappoport, A.: Semi-supervised recognition of sarcastic sentences on Twitter and Amazon. In: Proceedings of the Fourteenth Conference on Computational Natural Language Learning, Uppsala, Sweden, 15–16 July 2010, Association for Computational Linguistics, pp. 107–116 (2010)
https://www.dictionary.cambridge.org. Accessed 15 Mar 2021
https://www.github.com/aadityaubhat/medium_articles/tree/master/sarcasm_detection. Accessed 18 Mar 2021
https://www.kaggle.com/rmisra/news-headlines-dataset-for-sarcasm-detection. Accessed 21 Mar 2021
https://www.macmillandictionary.com. Accessed 10 Mar 2021
https://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow. Accessed 10 Mar 2021
Kim Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), October 2014, Doha, Qatar. Association for Computational Linguistics, pp. 1746–1751 (2014)
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations ICLR, San Diego, pp. 1–15 (2015)
McLaughlin, H.: Smog grading: a new readability formula. J. Reading 12(8), 639–646 (1969)
Oprea S., Magdy W.: iSarcasm: A Dataset of Intended Sarcasm (2019)
Rajadesingan, A., Zafarani, R., Huan Liu, H.: Sarcasm detection on Twitter: a behavioral modeling approach. In: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining February 2015, WSDM 2015, pp. 97–106 (2015)
Rockwell, P.: The Effects of Cognitive Complexity and Communication Apprehension on the Expression and Recognition of Sarcasm, Nova Science Publishers, Hauppauge (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mazurkiewicz, J., Woszczyna, J. (2021). Softcomputing Approach to Sarcasm Analysis. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds) Theory and Engineering of Dependable Computer Systems and Networks. DepCoS-RELCOMEX 2021. Advances in Intelligent Systems and Computing, vol 1389. Springer, Cham. https://doi.org/10.1007/978-3-030-76773-0_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-76773-0_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76772-3
Online ISBN: 978-3-030-76773-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)