Sarcastic Text Detection Using Keras

Yıl 2021, Cilt: IDAP-2021 : 5th International Artificial Intelligence and Data Processing symposium Sayı: Special, 126 - 131, 20.10.2021

Abdullah Erhan Akkaya

https://doi.org/10.53070/bbd.990890

Öz

Sarcastic text is a type of text that contains a kind of irony, in which negative expressions are expressed as positive by attributing meanings to words that contradict their real meanings during communication. During face-to-face communication, changes in tone of voice, body language, eye contact or word stress make it easier for the other person to detect the sarcastic expression. However, it is challenging to detect sarcastic expressions only through text in machine learning-based systems since human-centred qualities cannot be transferred. Newspapers often use sarcastic expressions in their headlines to attract people's attention. However, many people cannot fully understand whether these expressions are sarcastic or not without reading the content of the text. As a result, they can transmit false information to the people around them through direct communication or social media. In this study, to prevent such misinformation, newspaper headlines with and without sarcasm are tried to be classified on three different GPUs with deep learning methods. As a result, the developed model can successfully detect news headlines containing sarcasm.

Anahtar Kelimeler

Sarcastic text detection, Deep learning, Sentiment analysis.

Keras Kullanarak Kinayeli Metin Tespiti

Öz

Kinayeli metin, iletişim esnasında kelimelere gerçek anlamlarıyla çelişecek manalar yükleyerek, olumsuz ifadelerin olumlu gibi ifade edildiği bir çeşit ironi içeren metin türüdür. Yüz yüze iletişim esnasında, ses tonu, vücut dili, göz teması veya kelime vurgularında meydana gelen değişiklikler, karşıdaki kişinin kinayeli ifadeyi tespit etmesini kolaylaştırmaktadır. Bununla birlikte, makine öğrenmesine dayalı sistemlerde, insan merkezli niteliklerin aktarımı sağlanamadığından, kinayeli ifadeleri sadece metin üzerinden tespit etmek zordur. Gazeteler, insanların ilgisini çekebilmek için manşetlerinde genellikle kinayeli ifadeleri kullanmaktadır. Fakat birçok insan bu ifadelerin gerçekten kinayeli olup olmadığını, metnin içeriğini okumadan tam olarak anlayamamaktadır. Bunun sonucu olarak, çevresindeki insanlara karşılıklı iletişim veya sosyal medya üzerinden yanlış bilgi aktarabilmektedir. Bu çalışmada, bu tür yanlış bilgi yayılımının önüne geçebilmek için, kinayeli ve kinayeli olmayan gazete başlıkları, derin öğrenme yöntemleri ile üç farklı GPU üzerinde ayırt edilmeye çalışılmıştır. Sonuç olarak geliştirilen model, kinaye içeren haber başlıklarını başarılı bir şekilde tespit edebilmektedir.

Anahtar Kelimeler

Kinayeli metin tespiti, Derin öğrenme, Duygu analizi.

Kaynakça

• Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Zheng, X. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. https://arxiv.org/abs/1603.04467v2
• Andrej, K. (n.d.). Commonly used activation functions. Retrieved July 26, 2021, from http://cs231n.github.io/linear-classify/#loss
• Das, D., & Clark, A. J. (2018). Sarcasm detection on Flickr using a CNN. ACM International Conference Proceeding Series, 56–61. https://doi.org/10.1145/3277104.3277118
• Dictionary of Turkish Language Association. (n.d.). Retrieved August 8, 2021, from https://sozluk.gov.tr/
• Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep Sparse Rectifier Neural Networks (pp. 315–323). JMLR Workshop and Conference Proceedings. http://proceedings.mlr.press/v15/glorot11a.html
• Ilić, S., Marrese-Taylor, E., Balazs, J. A., & Matsuo, Y. (2018). Deep contextualized word representations for detecting sarcasm and irony. 2–7. https://arxiv.org/abs/1809.09795v1
• Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings. https://arxiv.org/abs/1412.6980v9
• Mandal, P. K., & Mahto, R. (2019). Deep CNN-LSTM with Word Embeddings for News Headline Sarcasm Detection. Advances in Intelligent Systems and Computing, 800 Part F1, 495–498. https://doi.org/10.1007/978-3-030-14070-0_69
• Maynard, D., & Greenwood, M. A. (2014). Who cares about sarcastic tweets? Investigating the impact of sarcasm on sentiment analysis. Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014, 4238–4243.
• Poria, S., Cambria, E., Hazarika, D., & Vij, P. (2016). A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks. COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers, 1601–1612. https://arxiv.org/abs/1610.08815v2
• SARCASM | Definition of SARCASM by Oxford Dictionary on Lexico.com also meaning of SARCASM. (n.d.). Retrieved August 8, 2021, from https://www.lexico.com/definition/sarcasm
• Tay, Y., Luu, A. T., Hui, S. C., & Su, J. (2018). Reasoning with Sarcasm by Reading In-Between. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 1, 1010–1020. https://doi.org/10.18653/V1/P18-1093