Analisis Sentimen Tentang Opini Performa Klub Sepak Bola Pada Dokumen Twitter Menggunakan Support Vector Machine Dengan Perbaikan Kata Tidak Baku

Swandy Raja Manaek Pakpahan (Fakultas Ilmu Komputer, Universitas Brawijaya)
Indriati Indriati (Fakultas Ilmu Komputer, Universitas Brawijaya)
Marji Marji (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 3 No 7 (2019): Juli 2019

Football is one of the most popular sports in the world, including in Indonesia. A football club is very dependent on its supporters so that the satisfaction of supporters of a football club must be maintained. Supporters of football clubs themselves often provide arguments to a football club via Twitter media. Therefore, the authors propose research to build a sentiment analysis system for football club performance opinions on Twitter documents. This research uses the Support Vector Machine method and Levenshtein Distance for non-standard word correction. The process starts with preprocessing the data, then do word correction with Levenshtein Distance, weighting using Term Frequency-Inverse Document Frequency, followed by classification using Support Vector Machine. The test results with the highest accuracy were obtained at 83.25% with learning rate = 0,0001, complexity = 0,001, lambda = 0,1, epsilon = 0,0001 and maximum iteration = 50.