Open access Jurnal SINTA 2
Analisis Sentimen Terhadap Pendapat Masyarakat Mengenai Pilkada 2024 Menggunakan Metode Support Vector Machine
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 12 No. 4 (2025) · pp. 809–818
- ISSN
- 2528-6579, 2355-7699
- Published
- 2025-08-29
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Bahasa Indonesia
Pemilihan Kepada Daerah dan Wakil Kepala Daerah, atau yang lebih dikenal sebagai Pilkada, merupakan pemilihan umum di Indonesia yang dilakukan secara langsung oleh masyarakat yang telah memenuhi ketentuan peraturan perundang-undangan. Twitter/X sebagai platform media sosial yang penting dalam komunikasi digital di Indonesia, menjadi tempat bagi masyarakat untuk menyuarakan pendapat mereka, termasuk pendapat mengenai pilkada. Tujuan penelitian ini adalah menganalisis sentimen masyarakat terhadap Pilkada melalui data yang dikumpulkan dari Twitter/X, serta memberikan wawasan berharga bagi pembuat kebijakan dan pemangku kepentingan dalam merespons aspirasi masyarakat. Analisis sentimen ini diharapkan dapat membantu memahami persepsi publik serta meningkatkan partisipasi dan kepercayaan masyarakat terhadap proses demokrasi. Penelitian ini dimulai dengan pengumpulan data dari Twitter/X. Proses berikutnya melibatkan enam tahap pre-processing, seperti case folding, pembersihan data, tokenizing, slang normalization, stemming, dan filtering. Metode klasifikasi menggunakan Support Vector Machine (SVM) dan pembobotan kata menggunakan Term Frequency-Inverse Document Frequency (TF-IDF) dengan menerapkan teknik oversampling dengan SMOTE untuk menyeimbangkan data. Hasil pengujian SVM berhasil mendapatkan performa tinggi dengan tingkat akurasi sekitar 93,09%, precision sekitar 93,13%, recall sekitar 93,09%, dan f1-score sekitar 93,08%. Analisis menggunakan Root Cause Analysis (RCA) terhadap empat aspek utama: kandidat, kebijakan dan regulasi, proses Pilkada, serta partai politik. Hasil analisis mengungkapkan sumber ketidakpuasan masyarakat terkait Pilkada, termasuk kekhawatiran akan kurangnya pengalaman kandidat, perubahan undang-undang yang dianggap tidak transparan, kelemahan dalam verifikasi identitas pemilih selama proses Pilkada, serta tuntutan untuk peningkatan komunikasi dan kinerja partai politik. Abstract The election of Regional Heads and Deputy Regional Heads, commonly known as Pilkada, is a general election in Indonesia conducted directly by citizens who meet the legal requirements. Twitter/X, as a prominent social media platform in Indonesia's digital communication landscape, serves as a platform for the public to express their opinions, including those about Pilkada. The aim of this study is to analyze public sentiment towards Pilkada using data collected from Twitter/X to provide valuable insights for policymakers and stakeholders in responding to public aspirations. This sentiment analysis is expected to help understand public perceptions and enhance participation and trust in the democratic process. The research begins with data collection from Twitter/X, followed by six pre-processing stages: case folding, data cleaning, tokenizing, slang normalization, stemming, and filtering. The classification method utilizes Support Vector Machine (SVM) and word weighting through Term Frequency-Inverse Document Frequency (TF-IDF), with oversampling techniques using SMOTE to balance the data. The SVM testing results achieved high performance with an accuracy rate of approximately 93,09%, precision of 93,13%, recall of 93,09%, and an f1-score of 93,08%. An analysis using Root Cause Analysis (RCA) was conducted on four key aspects: candidates, policies and regulations, the Pilkada process, and political parties. The analysis revealed sources of public dissatisfaction related to Pilkada, including concerns over candidates' lack of experience, perceived opacity in legislative changes, weaknesses in voter identity verification during the Pilkada process, and demands for improved communication and performance from political parties.
English
Pemilihan Kepada Daerah dan Wakil Kepala Daerah, atau yang lebih dikenal sebagai Pilkada, merupakan pemilihan umum di Indonesia yang dilakukan secara langsung oleh masyarakat yang telah memenuhi ketentuan peraturan perundang-undangan. Twitter/X sebagai platform media sosial yang penting dalam komunikasi digital di Indonesia, menjadi tempat bagi masyarakat untuk menyuarakan pendapat mereka, termasuk pendapat mengenai pilkada. Tujuan penelitian ini adalah menganalisis sentimen masyarakat terhadap Pilkada melalui data yang dikumpulkan dari Twitter/X, serta memberikan wawasan berharga bagi pembuat kebijakan dan pemangku kepentingan dalam merespons aspirasi masyarakat. Analisis sentimen ini diharapkan dapat membantu memahami persepsi publik serta meningkatkan partisipasi dan kepercayaan masyarakat terhadap proses demokrasi. Penelitian ini dimulai dengan pengumpulan data dari Twitter/X. Proses berikutnya melibatkan enam tahap pre-processing, seperti case folding, pembersihan data, tokenizing, slang normalization, stemming, dan filtering. Metode klasifikasi menggunakan Support Vector Machine (SVM) dan pembobotan kata menggunakan Term Frequency-Inverse Document Frequency (TF-IDF) dengan menerapkan teknik oversampling dengan SMOTE untuk menyeimbangkan data. Hasil pengujian SVM berhasil mendapatkan performa tinggi dengan tingkat akurasi sekitar 93,09%, precision sekitar 93,13%, recall sekitar 93,09%, dan f1-score sekitar 93,08%. Analisis menggunakan Root Cause Analysis (RCA) terhadap empat aspek utama: kandidat, kebijakan dan regulasi, proses Pilkada, serta partai politik. Hasil analisis mengungkapkan sumber ketidakpuasan masyarakat terkait Pilkada, termasuk kekhawatiran akan kurangnya pengalaman kandidat, perubahan undang-undang yang dianggap tidak transparan, kelemahan dalam verifikasi identitas pemilih selama proses Pilkada, serta tuntutan untuk peningkatan komunikasi dan kinerja partai politik. Abstract The election of Regional Heads and Deputy Regional Heads, commonly known as Pilkada, is a general election in Indonesia conducted directly by citizens who meet the legal requirements. Twitter/X, as a prominent social media platform in Indonesia's digital communication landscape, serves as a platform for the public to express their opinions, including those about Pilkada. The aim of this study is to analyze public sentiment towards Pilkada using data collected from Twitter/X to provide valuable insights for policymakers and stakeholders in responding to public aspirations. This sentiment analysis is expected to help understand public perceptions and enhance participation and trust in the democratic process. The research begins with data collection from Twitter/X, followed by six pre-processing stages: case folding, data cleaning, tokenizing, slang normalization, stemming, and filtering. The classification method utilizes Support Vector Machine (SVM) and word weighting through Term Frequency-Inverse Document Frequency (TF-IDF), with oversampling techniques using SMOTE to balance the data. The SVM testing results achieved high performance with an accuracy rate of approximately 93,09%, precision of 93,13%, recall of 93,09%, and an f1-score of 93,08%. An analysis using Root Cause Analysis (RCA) was conducted on four key aspects: candidates, policies and regulations, the Pilkada process, and political parties. The analysis revealed sources of public dissatisfaction related to Pilkada, including concerns over candidates' lack of experience, perceived opacity in legislative changes, weaknesses in voter identity verification during the Pilkada process, and demands for improved communication and performance from political parties.
Keywords
Collaboration network of the authors
40 authors · 79 co-authorship links · 16 across different organisations · showing the 40 most connected
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Institut Teknologi Sepuluh Nopember
- Universitas Muhammadiyah Malang
- National Research and Innovation Agency
- Affiliation unknown
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Admaja Dwi Herlambang | University of Brawijaya | 5 |
| Yusi Tyroni Mursityo | University of Brawijaya | 3 |
| Satrio Agung Wicaksono | University of Brawijaya | 3 |
| Nanang Yudi Setiawan | University of Brawijaya | 3 |
| Fahrur Rozi | Institut Teknologi Sepuluh Nopember | 2 |
| Septiyan Andika Isanta | Universitas Muhammadiyah Malang | 2 |
| Indriati . | Affiliation unknown | 2 |
| Aditya Rachmadi | University of Brawijaya | 2 |
| Faizatul Amalia | University of Brawijaya | 2 |
| Marji . | University of Brawijaya | 1 |
| Lailil Muflikhah | University of Brawijaya | 1 |
| Diana Purwitasari | Institut Teknologi Sepuluh Nopember | 1 |
| Yufis Azhar | Universitas Muhammadiyah Malang | 1 |
| Putri Nur Fadila | University of Brawijaya | 1 |
| Zikfikri Yulfiandi Rachmad | University of Brawijaya | 1 |
| Achmad Arwan | University of Brawijaya | 1 |
| Mahendra Data | University of Brawijaya | 1 |
| Ibnu Aqli | University of Brawijaya | 1 |
| Suherni Prahesti | University of Brawijaya | 1 |
| Heru Nurwasito | University of Brawijaya | 1 |
| Sutrisno Sutrisno | University of Brawijaya | 1 |
| Rozaq Akbar | University of Brawijaya | 1 |
| Cindy Felita Nur Alimah | University of Brawijaya | 1 |
| Muhammad Rosyid Mubarok | University of Brawijaya | 1 |
| Anisah Ikhsawiyanthi | University of Brawijaya | 1 |
| Pratama Aprilianto | University of Brawijaya | 1 |
| Hanifah Muslimah Az-Zahra | University of Brawijaya | 1 |
| Alfansya Achmad Mulyadi | University of Brawijaya | 1 |
| Meilita Dwi Aryati | University of Brawijaya | 1 |
| Azka Azkiyah | University of Brawijaya | 1 |
| Ahmad Afif Supianto | University of Brawijaya | 1 |
| Abdul Harris Wicaksono | University of Brawijaya | 1 |
| Didik Krisnandi | National Research and Innovation Agency | 1 |
| Ana Heryana | National Research and Innovation Agency | 1 |
| Fatmawati Fatmawati | University of Brawijaya | 1 |
| Tsania Dzulkarnain | University of Brawijaya | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.