KLASIFIKASI BERITA MENGGUNAKAN SUPPORT VECTOR MACHINE UNTUK MENGETAHUI JENIS KONTEN E-GOVERNMENT
No Thumbnail Available
Date
2020-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The development of technology today has provided a lot of convenience, one of which
is in terms of the spread of news. Now, news delivery can be through the website. The
website makes it easy for people to access news and makes it easier for news service
providers to spread the word. This ease also results in the increase of news text
documents so that it takes the process of extracting information from a large set of data
into usable information. The extracting process can be done by utilizing text mining.
This research aims to classify documents using the Support Vector Machine (SVM)
method on the e-Government website managed directly by KEMKOMINFO-RI. Stages
in this study include data collection, data preprocessing, TF-IDF weighting,
classification with Support Vector Machine (SVM) and evaluation using confusion
matrix. Based on the results of the study, it was obtained that SVM method can be
implemented well in the classification of news categories with the highest performance
results namely the amount of training data more than testing data in the first data
sharing scenario with a data training ratio and testing data of 90% : 10% with a
classification accuracy score of 100% including the excellent classification group
Description
Keywords
News, Support Vector Machine, Confusion Matrix, Text Mining