Sentiment Analysis of Twitter Data Related to the Ratification of the TNI Bill Using Orange Data Mining

Abstract

Twitter is one of the social media platforms where users can post photos, videos and talk about current issues. One of the current issues is the issue of the ratification of the TNI Bill. The method used is naïve bayes with the help of the orange data mining application. Researchers managed to group 400 tweets from Twitter based on the sentiments and emotions contained in them. The results showed that responses were Negative with a total of 166 tweets, neutral sentiment reaching 140 tweets, and 94 tweets showing positive sentiment. If the percentage of polarity analysis is calculated, the results are as large, negative (41.5%), neutral (35%), and positive (23.5%). The Naïve Bayes model used is able to classify data with fairly good accuracy, which is 82%. Although there is still an imbalance in the amount of data between positive, negative, and neutral sentiments, in general this method is quite reliable for describing public opinion on social media. In addition, this study shows that Orange Data Mining can be a practical and effective tool in analyzing texts or opinions in cyberspace.