Development of sentiment analysis and sarcasm detection systems for social network users

Abstract

As one of the biggest data sources, conversations on social media can be used for various purposes, one of which is sentiment analysis. By utilizing sentiment analysis, we can obtain an overview of public opinion on certain topics, such as business and politics. Through sentiment analysis, text can be grouped into positive, negative, or neutral sentiments. Sarcasm can cause inaccurate classification of sentiment. In this study, we examined the effect of sarcasm detection on sentiment analysis accuracy. The dataset used in this study contains a group of 1000 Indonesian language Tweet. The features used for sarcasm detection are sentiment score and interjection words. The algorithm used for sarcasm detection is Random Forest. Sentiment analysis was performed using the TF-IDF as the feature and the NaYve Bayes as the classification algorithm. The test results show that the sarcasm detection does not improve the accuracy of sentiment analysis. The average sentiment analysis accuracy is 74.3%. The average sentiment analysis accuracy with sarcasm detection is 72.9%. The average accuracy of sarcasm detection is 71.7%.