Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal JOURNAL OF SCIENCE AND SOCIAL RESEARCH Building of Informatics, Technology and Science
Mardiah, Nia
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Education Social Sciences

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

Found 2 Documents
Search

 1 
Analysis Of Indonesian People's Sentiment Towards 2024 Presidential Candidates On Social Media Using Naïve Bayes Classifier and Support Vector Machine Mardiah, Nia; Marlina, Leni; Khairul, Khairul; Sitorus, Zulham; Iqbal, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5766

Abstract

This research aims to analyze the sentiment of the Indonesian public towards the 2024 presidential candidates on social media platforms X and Instagram. The main issue addressed is how to determine public opinion as disseminated on social media regarding the presidential candidates. To address this issue, two classification methods are used: Naïve Bayes Classifier and Support Vector Machine (SVM). The objective of this research is to measure public sentiment, both positive and negative, towards the 2024 presidential candidates using these two methods. The research findings indicate that the implementation of the Naïve Bayes method with manual labeling achieved the highest accuracy of 86% for X data and 85% for Instagram comments data. Meanwhile, with lexicon-based labeling, the highest accuracy was 60% for both X and Instagram data. The SVM method with manual labeling also achieved the highest accuracy of 86% for X data and 85% for Instagram data. With lexicon-based labeling, the highest accuracy was 60% for X data and 70% for Instagram data. This research concludes that both Naïve Bayes and SVM demonstrate strong performance in sentiment analysis on social media, with SVM slightly outperforming in some scenarios. The implementation of these two methods provides valuable insights into public opinion towards the 2024 presidential candidates on social media.
ANALISIS SENTIMEN PENGGUNA INSTAGRAM TERHADAP STATEMENT MENTERI KEUANGAN TENTANG “KEBIJAKAN GAJI GURU DAN DOSEN” MENGGUNAKAN NAÏVE BAYES Santoso, M. Imam; Mardiah, Nia; Sembiring, Asha
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4385

Abstract

Abstract: The Minister of Finance's statement regarding the teacher and lecturer salary policy sparked mixed public reactions, particularly on social media. This study aims to analyze the sentiment of the Indonesian public, particularly Instagram users, regarding this statement using the Nae Bayes algorithm. Data was collected through scraping using Instant Data Scrapper in August 2025, totaling 939 data points. Preprocessing steps included cleansing, tokenizing, stopword removal, and stemming. The data were then classified into two sentiment categories: positive and negative. The results showed that the majority of Instagram user sentiment tended to be negative (859 data points, representing 91.5%), while positive sentiment accounted for 89 data points, representing 9.5%. The Nae Bayes model achieved an accuracy of 0.87 in classifying public opinion. These findings indicate that the Nae Bayes algorithm is effective in analyzing public opinion on sensitive issues on social media. Furthermore, the results of this study can serve as a reference for the government and policymakers in understanding public perception and formulating more appropriate communication strategies related to education policy. Keyword: Sentiment Analysis, Nae Bayes, Minister of Finance, Instagram, Text Analysis. Abstrak: Pernyataan Menteri Keuangan tentang kebijakan gaji guru dan dosen memicu beragam reaksi publik, khususnya di media sosial. Penelitian ini bertujuan untuk menganalisis sentimen masyarakat Indonesia, terutama pengguna Instagram, terhadap pernyataan tersebut dengan menggunakan algoritma Nae Bayes. Data dikumpulkan melalui proses scraping menggunakan Instant Data Scrapper pada Agustus 2025 dengan jumlah 939 data. Kemudian dilakukan tahap praproses meliputi cleansing, tokenizing, stopword removal, dan stemming. Selanjutnya, data diklasifikasikan ke dalam dua kategori sentimen, yaitu positif dan negatif. Hasil penelitian menunjukkan bahwa mayoritas sentimen pengguna Instagram cenderung Negatif (859 data dengan persentase 91,5%), sedangkan sentimen positif berjumlah 89 data dengan persentase 9,5%. Model Nae Bayes mencapai tingkat akurasi sebesar 0,87 dalam mengklasifikasikan opini publik. Temuan ini mengindikasikan bahwa algoritma Nae Bayes efektif dalam menganalisis opini publik pada isu sensitif di media sosial. Selain itu, hasil penelitian ini dapat menjadi acuan bagi pemerintah dan pemangku kebijakan dalam memahami persepsi publik serta merumuskan strategi komunikasi yang lebih tepat terkait kebijakan pendidikan. Kata kunci: Sentimen Analisis, Nae Bayes, Menteri Keuangan, Instagram, Analisis Teks.
Co-Authors Khairul Khairul, Khairul Santoso, M. Imam Sembiring, Asha Sitorus, Zulham Winnugroho Wiratman, Manfaluthy Hakim, Tiara Aninditha, Aru W. Sudoyo, Joedo Prihartono