Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
M. Rizzo Irfan
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 Kurikulum 2013 pada Twitter menggunakan Ensemble Feature dan Metode K-Nearest Neighbor M. Rizzo Irfan; Mochammad Ali Fauzi; Tibyani Tibyani
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (368.047 KB)

Abstract

The 2013 curriculum is a new curriculum in the Indonesian education system that has been enacted by the government to replace the 2006 curriculum or the Education Unit Level Curriculum. The implementation of this curriculum in recent years has sparked controversy in Indonesian education, students who are demanded more actively, added lessons and other matters that lead to various opinions that develop in the community, especially on Twitter. An estimated 200 million Twitter users post 400 million tweets per day. In this research, sentiment analysis is conducted to find out the developing opinion which is divided into positive opinion or negative opinion. The features and methods used are the ensemble feature and the K-Nearest Neighbor (K-NN) classification method. Ensemble feature is a combined feature, in the form of statistical Bag of Words (BoW) and semantic features (twitter specific, textual features, PoS features, lexicon based features). Based on a series of tests, the combination of features has an impact in improving the accuracy of the K-Nearest Neighbor (K-NN) method for determining positive or negative opinions. Merging this feature can complement the weaknesses of each feature, so the final result of accuracy gained by combining both features reaches 96%. In contrast to using only features independently, the accuracy achieved only reaches 80% on Bag of Words (BoW) features and 82% on ensemble features without Bag of Words (BoW).
Co-Authors M. Ali Fauzi Tibyani Tibyani