A Research on Detection of Sarcasm using Machine Learning Techniques
Amruta K. Chimote1, S.R. Tandan2
1Amruta K. Chimote, Research Scholar, Department of Computer Science & Engineering, Dr. C.V. Raman University, Bilaspur (Chhattisgarh), India.
2S. R. Tandan, Associate Professor, Department of Computer Science & Engineering, Dr. C.V. Raman University, Bilaspur (Chhattisgarh), India.
Manuscript received on 12 October 2019 | Revised Manuscript received on 21 October 2019 | Manuscript Published on 02 November 2019 | PP: 968-971 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B11600982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1160.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Today in the era of flooding information on online forums, social media where decision making of customer(user) is assisted in all possible ways. Almost all types of applications have their own assistant or chatbots to guide user for his/her query. Use of assistants and chatbots gives real experience and at the same time for admin it is performing the role of customer care executive. To make it more realistic most of assistants and chatbots are built in conversational format which guide user to get correct information. It is necessary to have knowledge of user sentiments while assistance is provided. Sarcasm is one of complex human sentiment which is used to convey disagreement using positive words. This paper provides review on various approaches used to detect sarcasm present in textual data using supervised and unsupervised approaches of machine learning. It is observed many authors used neural networks algorithms to detect sarcasm. Efficiency and accuracy of detection can be increased with combination of different approaches.
Keywords: Machine Learning Sarcasm Neural Networks.
Scope of the Article: Machine Learning