Identification of Hypertension Treatment Using Linguistic

Abstract

Text mining is an obscure data or procedure to acquire data from the information that we have received. Text mining can combine

information from numerous sources. There are two techniques that have been used in text mining which is information extraction and

classification. For information extraction, RStudio is used. The method that RStudio uses is tm_map as a median to extract the term keyword.

For classification, Support Vector Machine (SVM) is used. Waikato Environment for Knowledge Analysis (WEKA) will act as a tool for

SVM to classify the treatment. There are many algorithms in WEKA that will give different results. Therefore, the purpose of this research is

to identify whether medical drug or natural remedy is the best treatment.