Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi
Ammar Sufyan
Universitas Islam Negeri Syarif Hidayatullah Jakarta
Computer Science & IT

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

Found 1 Documents
Search

 1 
Sentimen Analisis Twitter Ibu Kota Negara Nusantara Menggunakan Long Short-Term Memory dan Lexicon Based Saepul Aripiyanto; Tukino Tukino; Ammar Sufyan; Riandi Nandaputra
EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi Vol 12, No 2 (2022): December
Publisher : Universitas Bandar Lampung (UBL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36448/expert.v12i2.2821

Abstract

In the 2020 APJII Survey, Indonesians who use Twitter for social media are 10% of the entirety of social media users in Indonesia (APJII 2020), the issue that is being discussed a lot both on social media and offline discussions, is the National Capital City (IKN) of the Archipelago, which is the new capital city of the Republic of Indonesia. The relocation of the capital city raises pros and cons. With these pros and cons, an analysis of public sentiment regarding the IKN issue becomes a necessity. In this research, the model that will be used to analyze sentiment analysis uses the Long Short Term Memory (LSTM) algorithm and lexicon based on two scenarios, which is the scenario that uses 100 data of tweets and 5112 data of tweets. The results for the 100 tweets dataset scenario obtained 64% accuracy, 40% precision, 64% recall, and 79% F1-Score. Meanwhile, the results for the 5112 tweets data scenario obtained 79% accuracy, 82% precision, 79% recall, 79% F1-Score. The sentiment results obtained from the 5112 tweets data are 44.8% positive sentiment, 36.2% negative sentiment and 19.0% neutral sentiment. Based on this research, the number of datasets will affect the performance of deep learning models built using lexicon based and LSTM algorithms.
Co-Authors Riandi Nandaputra Saepul Aripiyanto Tukino