PROJECT TITLE :

Text Mining Based on Tax Comments as Big Data Analysis Using SVM and Feature Selection - 2018

ABSTRACT:

The tax provides an important role for the contributions of the economy and development of a rustic. The improvements to the taxation service system continuously done in order to extend the State Budget. One of thought to know the performance of taxation significantly in Indonesia is to grasp the general public opinion as for the item service. Text mining can be used to understand public opinion regarding the tax system. The rapid growth of knowledge in social media initiates this research to use the info source as big data analysis. The dataset used comes from Facebook and Twitter as a supply of information in processing tax comments. The results of opinions in the shape of public sentiment in part of service, web site system, and news will be used as consideration to improve the quality of tax services. During this research, text mining is completed through the phases of text processing, feature selection and classification with Support Vector Machine (SVM). To cut back the matter of the number of attributes on the dataset in classifying text, Feature Selection used the information Gain to select the relevant terms to the tax topic. Testing is used to live the performance level of SVM with Feature Selection from two knowledge sources. Performance measured using the parameters of precision, recall, and F-live.