ALGORITMA SUPPORT VECTOR MACHINE BERBASIS ALGORITMA GENETIKA UNTUK ANALISIS SENTIMEN PADA TWITTER

Abstract

Millions of users Twitter account is now able to share their thoughts and opinions on various aspects, because twitter is regarded as a rich source of information for decision making and sentiment analysis. Sentiment in the present study aims to overcome the problem of users into groups tweet positive opinion and a negative opinion. Classifier Support Vector Machine (SVM) is a learning technique that classifies the text being popular research field Text Mining. However Support Vector Machine (SVM) has a weakness in the right parameter selection problem. The trend in recent years is to simultaneously optimize the features and parameters to Support Vector Machine (SVM), so as to improve the accuracy of classification Support Vector Machine (SVM). Genetic algorithms have the potential to produce better features and become the optimal parameters at the same time. This Penelitiana generate text classification in the form of positive and negative tweets on account of fast food restaurant McDonalds is an account. Accuracy of measurement on Support Vector Machine (SVM) before and after using Genetic Algorithms. Evaluation is done by using a 10 fold cross vadilation while the measurement accuracy is measured by the confusion matrix and ROC curves. The results showed an increase in the accuracy of Support Vector Machine (SVM) from 83.50% to 91.00%.