Indonesian Journal of Electrical Engineering and Computer Science Vol. 23, No. 2, August 2021, pp. 993~1001 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v23.i2.pp993-1001  993 Journal homepage: http://ijeecs.iaescore.com Sarcasm detection of tweets without #sarcasm: data science approach Rupali Amit Bagate 1 , R. Suguna 2 1,2 Department of Computer Science & Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai, India 1 Department of Information Technology, Army Institute of Technology, Dighi Hills, Pune, India Article Info ABSTRACT Article history: Received Feb 5, 2021 Revised May 24, 2021 Accepted Jun 1, 2021 Identifying sarcasm present in the text could be a challenging work. In sarcasm, a negative word can flip the polarity of a positive sentence. Sentences can be classified as sarcastic or non-sarcastic. It is easier to identify sarcasm using facial expression or tonal weight rather detecting from plain text. Thus, sarcasm detection using natural language processing is major challenge without giving away any specific context or clue such as #sarcasm present in a tweet. Therefore, research tries to solve this classification problem using various optimized models. Proposed model, analyzes whether a given tweet, is sarcastic or not without the presnece of hashtag sarcasm or any kind of specific context present in text. To achieve better results, we used different machine learning classification methodology along with deep learning embedding techniques. Our optimized model uses a stacking technique which combines the result of logistic regression and long short-term memory (LSTM) recurrent neural net feed to light gradient boosting technique which generates better result as compare to existing machine learning and neural network algorithm. The key difference of our research work is sarcasm detection done without #sarcasm which has not been much explored earlierby any researcher. The metrics used for evolution is F1-score and confusion matrix. Keywords: Dataset Deep learning Hashtag LSTM Machine learning Neural network Sarcasm detection This is an open access article under the CC BY-SA license. Corresponding Author: Rupali Amit Bagate Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai No. 42, Avadi-Vel Tech Road, Vel Nagar Chennai, Tamil Nadu 600062, India Email: rupali.bagate@gmail.com 1. INTRODUCTION Beginning of the internet gave a new vision to the world by changing the way people around the world interact. Now, people started expressing their feeling in front of other people to whom they even don't know. Also, people gather the opinion of each-others feeling, for a particular thing. It may be noted that for humans, it is easy to understand the opinion of other people. However, for a machine, it is very difficult to understand what people are says and how they feel. Sentiment analysis helps machine to analyze the written sentence and classifies it as a positive, negative, or neutral. Sentiment analysis gathers and recognizes attitudes and opinions depicted by users in social media toward a definitive topic. Research on sentiment analysis made machines capable of detecting whether a sentence is positive, negative, or neutral with a good accuracy depending upon the dataset. However it is very difficult to findthe exact sentiment, when the present sentence is layered with sarcasm, thus making it extremely difficult to find out whether the sentence is said in sarcastic manner or not [1].