Analisis Sentimen Tentang Opini Film Pada Dokumen Twitter Berbahasa Indonesia Menggunakan Naive Bayes Dengan Perbaikan Kata Tidak Baku

Prananda Antinasari (Fakultas Ilmu Komputer, Universitas Brawijaya)
Rizal Setya Perdana (Fakultas Ilmu Komputer, Universitas Brawijaya)
Mochammad Ali Fauzi (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 1 No 12 (2017): Desember 2017

The rapid growth of social media does not make Twitter left by its users. Twitter is one of the social media that allows user to interact each other, share information, or even to express feelings and opinions, including in expressing film opinions. Comments or Tweets about movies that exist on Twitter can be used as an evaluation in watching movies and increasing film production. To figure it out, sentiment analysis can be used to classify into negative or positive sentiments. In Tweets contain many languages ​​used in the form of non-standard languages ​​such as slang, word-outs, and misspellings. Therefore it takes special handling on Twitter comments. In this research used non-standard word dictionary and Levenshtein Distance normalization to improve non-standard word to standard word by classification Naive Bayes. Based on the result of the test, the highest accuracy, precision, recall, and f-measure value are 98.33%, 96.77%, 100%, and 98.36%.