KLASIFIKASI ARTIKEL HOAX MENGGUNAKAN SUPPORT VECTOR MACHINE LINEAR DENGAN PEMBOBOTAN TERM FREQUENCY – INVERSE DOCUMENT FREQUENCY

Rofie Sagara, Dina Maulina
UNIVERSITAS AMIKOM YOGYAKARTA.2017

A B S T R A C T

In the world of text mining is familiar with the term classification, which can perform grouping of text that has been given weight. one of the most commonly used algorithms for classification of text weights is the Support Vector Machine (SVM) and for weighting text using Term Frequency-Inverse Document Frequency (TF-IDF).

This research will use the algorithm to classify and weighting which will be implemented into android-based applications that will be used by users to classify articles on the internet.

From the results of the test using 108 hoax articles and 132 articles not hoax, the accuracy level obtained by using the calculation of Cross Validation with 10Fold is 95.8333% with support vector that is owned by the model is 14 support vectors.

Keyword: SVM, TF-IDF, Classification, Text Mining.

CategoryUndergraduate Thesis
Posted Date( undocumented )
Modified Date30 November 2017
Download File Publikasi_14.11.8030.pdf
Google Scholar