Abstract

Sarcasm can change the polarity of a sentence and it becomes the opposite. While sentiment analysis on social media has been widely used, but it is still rare to find sentiments and analyze them, considering the detection of sarcasm in it. Sarcasm detection in sentiment analysis is a challenging task. After successful identification of sarcasm the quality of sentiment analysis improves drastically. Experiments about sentiment analysis by detection of sarcasm are more often found in the language used in context with some special words. Therefore, taking into account research done on English tweets, this study analyzes the sentiment analysis sarcasm in Tweets agreed within context (specific topic) using the interjection and unigram features as features The main task is to detect sarcastic sentences and compare using classification methods namely Support Vector Machine with polynomial kernels. Thereafter incorporating interjection feature words that were expressing one's feelings and intentions and the unigram feature which is a collection of words a single obtained from the corpus automatically. Results of experiments show that the use of interjection features and unigram as detection of sarcasm in tweets using SVM will enhance the accuracy by 91%.