Sarcasm Detection in Twitter using Sentiment Analysis
Bala Durga Dharmavarapu1, Jayanag Bayana2

1Bala Durga Dharmavarapu, Department of CSE, V R Siddhartha Engineering College, Kanuru (Andhra Pradesh), India.
2Jayanag Bayana, Department of CSE, V R Siddhartha Engineering College, Kanuru (Andhra Pradesh), India.
Manuscript received on 05 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 642-644 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A11180681S419/2019©BEIESP
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 (

Abstract: Designing efficient and robust algorithms for detection of sarcasm on Twitter is the exciting challenge in opinion mining field. Sarcasm means the person speaks the contradictory of what the individual means, expressing gloomy feelings applying positive words. It helps the retailers to know the opinions of the customers. Sarcasm is widely used in many social networking and micro-blogging websites where people invade others which makes problematic for the individuals to say what it means. In the existing systems, logistic regression technique is used to detect these sarcastic tweets, it has a drawback as it cannot predict for continuous variables. In the proposed methodology Sentiment Analysis, Naive Bayes classification and AdaBoost algorithms are used to detect sarcasm on twitter. By using Naive Bayes classification, the tweets are categorized into sarcastic and non-sarcastic. The AdaBoost algorithm is used to make the weak statement to strong statements by iteratively considering the subset of training data. Sentiment Analysis is used to mine the opinions of customers to identify and extract information from the text. By using these two techniques, sarcastic statements can be easily classified and identified from twitter.
Keywords: Sarcasm, Sentiment Analysis, Naive Bayes Classification, AdaBoost, Twitter, Tweets.
Scope of the Article: Classification