Read ArtSciLab Member Omkar Ajnadkar's Recent Publication

"Sarcasm Detection of Media Text Using Deep Neural Networks" by: Omkar Ajnadkar

Abstract

Sarcasm detection in media text is a binary classification task where text can be either written straightly or sarcastically (with irony) where the intended meaning is the opposite of what is seemingly expressed. Performing sarcasm detection can be very useful in improving the performance of sentimental analysis where existing models fail to identify sarcasm at all. We examine the use of deep neural networks in this paper to detect the sarcasm in social media text(specifically Twitter data) as well as news headlines and compare the results. Results show that deep neural networks with the inclusion of word embeddings, bidirectional LSTM’s and convolutional networks achieve better accuracy of around 88 percent for sarcasm detection.

---

Read the entire paper here using this link

---

Ajnadkar O. (2021) Sarcasm Detection of Media Text Using Deep Neural Networks. In: Mandal J.K., Mukherjee I., Bakshi S., Chatterji S., Sa P.K. (eds) Computational Intelligence and Machine Learning. Advances in Intelligent Systems and Computing, vol 1276. Springer, Singapore. https://doi.org/10.1007/978-981-15-8610-1_6