Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Tania Malik Iryana
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Sentimen Masyarakat Terhadap Mass Rapid Transit Jakarta Menggunakan Metode Naive Bayes Dengan Normalisasi Kata Tania Malik Iryana; Indriati Indriati; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 6 (2021): Juni 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Since the Jakarta mass rapid transit (MRT) was operated, there have been various opinions from the public regarding facilities and services of the Jakarta MRT which have been conveyed through social media such as Twitter, Instagram, TikTok, and YouTube. In writing opinions on social media, errors are often found such as slang words, abbreviated words, and typographical errors which can complicate the classification process. Based on that thing, this research will use word normalization with a dictionary of slang words and abbreviations and also use word normalization with Peter Norvig. Opinions that have been conveyed by the public must be analyzed properly in order to produce useful information for PT MRT Jakarta. In conducting sentiment analysis, a classification method is needed and the classification method to be used is the Naive Bayes method. Testing in this research used 5-fold and for each fold 200 training data and 50 test data were used. Based on the test results, it can be concluded that the classification is better to use word normalization because the existence of word normalization can equate two words that have the same meaning so that it can increase the weight of the words. The 5-fold average evaluation results of the Naive Bayes classification with word normalization using a dictionary of slang words and abbreviations and also word normalization using Peter Norvig yielded 0.903 for precision, 0.944 for recall, 0.922 for f-measure, and 0.903 for accuracy.
Co-Authors Indriati Indriati Putra Pandu Adikara