Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Muhammad Kevin Sandryan
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 Pada Media Sosial Twitter Terhadap Undang-Undang Cipta Kerja Menggunakan Algoritma Backpropagation dan Term Frequency-Inverse Document Frequency Muhammad Kevin Sandryan; Bayu Rahayudi; Dian Eka Ratnawati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 2 (2021): Februari 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Social media is a platform for people to sharing their views on certain things or events. One of the things discussed on social media is the Job Creation Law (UU Cipta Kerja). The Job Creation Law is a law that simplifies regulations related to licensing activities in starting a business and investing with the aim of increasing Indonesia's economic growth. Twitter is a social media where many users share their opinions regarding the Job Creation Law. Therefore, Twitter can be a source for analyzing user opinions regarding the Job Creation Law. This research was conducted to analyze the sentiment on tweets (a term for content uploaded to Twitter) regarding the Job Creation Law by classifying tweets into two categories, positive and negative sentiment. The classification process is done by implementing an Artificial Neural Network (ANN) trained by Backpropagation algorithm and term weighting using Term Frequency-Inverse Document Frequency (TF-IDF) method into Python. There are several stages in this study, there are data scrapping, data labeling, preprocessing, term weighting, training, testing, and performance evaluation. The best performance obtained by the ANN is 95% accuracy, 98% precision, 92.4% recall, and 95.1% f-measure. This value was obtained when the ANN trained with 1500 epochs, 1 hidden layer with 50 hidden nodes, and 0.2 learning rate
Co-Authors Bayu Rahayudi Dian Eka Ratnawati