Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA
Satyananda, Karuna Dewa
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Public Sentiment Dynamics: Analysis of Twitter/X Data on the 2024 Indonesian Election with NB-SVM Satyananda, Karuna Dewa; Sibaroni, Yuliant
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7710

Abstract

This research analyzes the dynamics of public sentiment towards three pairs of presidential candidates in the 2024 Indonesian Election. This research was conducted using Twitter data as a source of information to gain a deeper understanding of the pattern of public sentiment during six crucial phases in the context of the election. The data is analyzed periodically during the election period. Sentiment analysis was carried out using the Naïve Bayes-Support Vector Machine classification approach to understand the sentiment patterns that emerged in each phase. NB-SVM utilizes class frequency information from NB to weight features, then trains separate SVMs for each class using these weighted features, improving classification accuracy. Models using NB-SVM classification produce better accuracy than models using NB and SVM classification, with an average accuracy of 76%. In Pair 01, a dynamic pattern was formed, namely a decrease in the level of positive sentiment during the debate and increasing again at a later time. Meanwhile, for Pair 02 and 03, a pattern was not formed for different reasons, namely sentiment that was too stable for Pair 02, and unstable sentiment for Pair 03. While Pair 01 obtained the most positive sentiment, Pair 02 received the most negative, with an average of 65.19% during the election process. This research proves that the results of sentiment analysis on Twitter/X contradict the official results by KPU of the general election in Indonesia.
Public Sentiment Dynamics: Analysis of Twitter/X Data on the 2024 Indonesian Election with NB-SVM Satyananda, Karuna Dewa; Sibaroni, Yuliant
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7710

Abstract

This research analyzes the dynamics of public sentiment towards three pairs of presidential candidates in the 2024 Indonesian Election. This research was conducted using Twitter data as a source of information to gain a deeper understanding of the pattern of public sentiment during six crucial phases in the context of the election. The data is analyzed periodically during the election period. Sentiment analysis was carried out using the Naïve Bayes-Support Vector Machine classification approach to understand the sentiment patterns that emerged in each phase. NB-SVM utilizes class frequency information from NB to weight features, then trains separate SVMs for each class using these weighted features, improving classification accuracy. Models using NB-SVM classification produce better accuracy than models using NB and SVM classification, with an average accuracy of 76%. In Pair 01, a dynamic pattern was formed, namely a decrease in the level of positive sentiment during the debate and increasing again at a later time. Meanwhile, for Pair 02 and 03, a pattern was not formed for different reasons, namely sentiment that was too stable for Pair 02, and unstable sentiment for Pair 03. While Pair 01 obtained the most positive sentiment, Pair 02 received the most negative, with an average of 65.19% during the election process. This research proves that the results of sentiment analysis on Twitter/X contradict the official results by KPU of the general election in Indonesia.
Co-Authors Yuliant Sibaroni