Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Building of Informatics, Technology and Science
Maharani, Zahra Nabila
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sentiment Analysis of the 2024 Indonesian Presidential Dispute Trial Election using SVM and Naïve Bayes on Platform X Maharani, Zahra Nabila; Luthfiarta, Ardytha; Farsya, Nabila Zibriza
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5380

Abstract

Indonesian presidential dispute trial election are crucial activities in the democratic process where open exchanges of views and opinions occur. Sentiment analysis can help understand public opinion regarding these sessions. This study aims to conduct sentiment analysis of the 2024 Indonesian presidential dispute trial election using the Support Vector Machine (SVM) and Gausian Naïve Bayes (GNB) with Nazief Adriani and Sastrawi stemming methods on Platform X. The research addresses the challenge of uncertainty in interpreting public sentiment towards Indonesian presidential dispute trial election. SVM and GNB was chosen for its ability to classify large and complex data sets. The Nazief Andriani and Sastrawi stemming techniques were employed to reduce words to their base forms, thereby enhancing the quality of text analysis. The study was conducted on Platform X, which provides access to text data from various sources including social media and news platforms. The data used covered specific periods before, during, and after Indonesian presidential dispute trial election. The keywords used for the crawling process are “sidang sengketa pilpress”, “sidang sengketa pemilu”, and “sidang pilpres”. The classification technique is carried out by classifying it into two classes, namely positive and negative. In applying sentiment analysis using machine learning methods, there are several methods that are often used. Based on the results comparation of tests carried out on 2,443 tweets using SVM with Sastrawi stemming method produce the best accuracy of 91.1%, precision 90%, recall 91%., and F1-Score 91%.
Optimizing Sentiment Analysis of Working Hours Impact on Generation Z’s Mental Health Using Backpropagation Farsya, Nabila Zibriza; Luthfiarta, Ardytha; Maharani, Zahra Nabila; Ganiswari, Syuhra Putri
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.v8i3.7827

Abstract

The topic of working hours' impact, Generation Z, and mental health are discussions that are often found on social media such as X (used to be Twitter). The sentiment analysis addressing these topics is needed to find out people’s opinions regarding these topics. It could also be helpful as a consideration for the decision-making process for related topics research. Therefore, this research aims to improve the accuracy of the model generated by the previous sentiment analysis research regarding the working hours’ impact on Gen Z’s mental health. The contribution of this research is by building a robust Backpropagation Neural Network model and utilizing SMOTETomek to achieve higher accuracy. This research compared two oversampling techniques for data balancing: SMOTE and SMOTETomek. The result shows that this research has successfully outperformed the baseline research with the best accuracy of 91% using SVM by generating the best accuracy of 93.01% with SMOTETomek. For comparison, SMOTETomek has outperformed SMOTE by generating the best accuracy of 93.01%, while the best accuracy generated with SMOTE is 92.26%. It indicates that in the case of Indonesian text sentiment analysis of this research, SMOTETomek has a better effect compared to SMOTE.
Optimizing Sentiment Analysis of Working Hours Impact on Generation Z’s Mental Health Using Backpropagation Farsya, Nabila Zibriza; Luthfiarta, Ardytha; Maharani, Zahra Nabila; Ganiswari, Syuhra Putri
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.v8i3.7827

Abstract

The topic of working hours' impact, Generation Z, and mental health are discussions that are often found on social media such as X (used to be Twitter). The sentiment analysis addressing these topics is needed to find out people’s opinions regarding these topics. It could also be helpful as a consideration for the decision-making process for related topics research. Therefore, this research aims to improve the accuracy of the model generated by the previous sentiment analysis research regarding the working hours’ impact on Gen Z’s mental health. The contribution of this research is by building a robust Backpropagation Neural Network model and utilizing SMOTETomek to achieve higher accuracy. This research compared two oversampling techniques for data balancing: SMOTE and SMOTETomek. The result shows that this research has successfully outperformed the baseline research with the best accuracy of 91% using SVM by generating the best accuracy of 93.01% with SMOTETomek. For comparison, SMOTETomek has outperformed SMOTE by generating the best accuracy of 93.01%, while the best accuracy generated with SMOTE is 92.26%. It indicates that in the case of Indonesian text sentiment analysis of this research, SMOTETomek has a better effect compared to SMOTE.
Co-Authors Ardytha Luthfiarta Farsya, Nabila Zibriza Ganiswari, Syuhra Putri