Abstract
In recent years, significant improvements have been made in the field of sentiment analysis, particularly in computational humor. In this research work, an AI-based cross-cultural humor recognition model has been developed and implemented. The model consists of a Convolutional Neural Network that can assess whether a given sentence is humorous or not and whether the sentence has a western or Chinese type of humor. The model has been trained and tested over the created dataset composed of 463314 English sentences and 111614 Chinese sentences. The initial model setting reached an accuracy of 64,48%. The analysis of the obtained results showed the importance of three main contributors to the model accuracy, namely, the dataset variety, dimension and model’s hyperparameters. Finally, these contributors were optimized by various tests, resulting in the final model obtaining an accuracy of 96,73%. The flexibility of the model allows applications in several areas such as private social media for cross-cultural communication, cross-cultural marketing and even fake news detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Litman, D., Purandare, A.: Humor: prosody analysis and automatic recognition for F*R*I*E*N*D*S*. In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, Sydney (2006)
Kiddon, C., Brun, Y.: That’s what she said: double entendre identification. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL), Portland, pp. 89–94 (2011)
Oliveira, L.D., Rodrigo, A.: Humor Detection in Yelp Reviews (2015)
Bertero, D., Fung, P.: A long short-term memory framework for predicting humor in dialogues. In: North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference, pp. 130–135 (2016). https://doi.org/10.18653/v1/n16-1016
Giudice, V.: Humor detection in Spanish tweets with character-level convolutional RNN. In: ASPIE96 at HAHA (IberLEF 2019) - CEUR Workshop Proceedings, pp. 165–171 (2019)
Cignarella, A.T., Frenda, S., Basile, V., Bosco, C., Patti, V., Rosso, P.: Overview of the EVALita 2018 task on irony detection in Italian tweets (IRONITA). In: CEUR Workshop Proceedings (2018). https://doi.org/10.4000/books.aaccademia
Li, D., Rzepka, R., Ptaszynski, M., Araki, K.: Convolutional Neural Network for Chinese Sentiment Analysis Considering Chinese Slang Lexicon and Emoticons, pp. 2–5 (2019)
Li, D., Rzepka, R., Ptaszynski, M., Araki, K.: Emoticon-aware recurrent neural network model for Chinese sentiment analysis. In: 2018 9th International Conference on Awareness Science and Technology (ICAST 2018), pp. 161–166 (2018). https://doi.org/10.1109/ICAwST.2018.8517232
Kakkle Open Source Project. https://www.kaggle.com/abhinavmoudgil95/short-jokes
Europarl: First Conference on Machine Translation (WMT16). https://www.statmt.org/wmt16/translation-task.html
XiaoHua ZOL. https://xiaohua.zol.com.cn/
THU NLP Lab. https://github.com/thunlp/THUCTC
Zuckerberg, M.: Facebook to start detecting and labeling fake news (2017). https://whatsnewinpublishing.com/zuckerberg-pivots-facebook-to-start-detecting-and-labeling-fake-news/
Venkat, J.: Detection & Classification of Fake News Using Convolutional Neural Nets (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, R., Rau, PL.P. (2021). Deep Learning Model for Humor Recognition of Different Cultures. In: Rau, PL.P. (eds) Cross-Cultural Design. Experience and Product Design Across Cultures. HCII 2021. Lecture Notes in Computer Science(), vol 12771. Springer, Cham. https://doi.org/10.1007/978-3-030-77074-7_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-77074-7_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77073-0
Online ISBN: 978-3-030-77074-7
eBook Packages: Computer ScienceComputer Science (R0)