Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Prosiding Seminar Nasional Official Statistics
Meytry Petronella Purba
Unknown Affiliation
Humanities Computer Science & IT Economics, Econometrics & Finance Social Sciences

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

Found 1 Documents
Search

 1 
Analisis Basic Emotion Masyarakat Pada Masa Pandemi COVID-19 di Media Sosial Twitter Dengan Metode LSTM-FastText Meytry Petronella Purba; Yuliagnis Transver Wijaya
Seminar Nasional Official Statistics Vol 2022 No 1 (2022): Seminar Nasional Official Statistics 2022
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (680.038 KB) | DOI: 10.34123/semnasoffstat.v2022i1.1524

Abstract

The policy of restricting public activities, which was implemented during the pandemic, had negative effects related to the emotions and mental health of people at various levels. Emotional stability is a proxy indicator in measuring mental health. The pandemic has resulted in various psychological responses, one of which is an emotional response. So it is important to know what emotions are the most dominating in society. Therefore, this research was conducted to inform the community's basic emotions on Twitter social media with the Ekman emotion model, and to implement it with a deep learning algorithm, namely Long Short Term Memory (LSTM) with word embedding FastText. This study succeeded in finding the most dominant basic emotion of society is the category of happy emotions. And based on the model that has been built LSTM-FastText, it produces an accuracy of 99.24% and a loss of 0.0264. This illustrates that very small errors occur in classifying train data. And this model has been well used in analyzing the basic emotions of the community during the COVID-19 pandemic on Twitter social media
Co-Authors Yuliagnis Transver Wijaya