Analisis Sentimen Terhadap Pendapat Masyarakat Mengenai Pilkada 2024 Menggunakan Metode Support Vector Machine

Penulis

  • Eka Bayu Satriawan Universitas Brawijaya, Malang
  • Satrio Hadi Wijoyo Universitas Brawijaya, Malang
  • Dian Eka Ratnawati Universitas Brawijaya, Malang

DOI:

https://doi.org/10.25126/jtiik.124

Kata Kunci:

regional election, Root Cause Analysis, Sentiment Analysis, Support Vector Machine, twitter/x

Abstrak

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.

 

Downloads

Download data is not yet available.

Referensi

ATMOJO, M.I.T. and SINDUNINGRUM, E., 2023. Analisis Sentimen Tentang Penggunaan Galon Bebas BPA di Indonesia Menggunakan Algoritma Support Vector Machine. Jurnal Sistem Komputer dan Informatika (JSON), [online] 5(2), pp.394–403. https://doi.org/10.30865/JSON.V5I2.7101.

BRAHIMI, B., TOUAHRIA, M. and TARI, A., 2021. Improving sentiment analysis in Arabic: A combined approach. Journal of King Saud University - Computer and Information Sciences, 33(10), pp.1242–1250. https://doi.org/10.1016/J.JKSUCI.2019.07.011.

CAELEN, O., 2017. A Bayesian interpretation of the confusion matrix. Annals of Mathematics and Artificial Intelligence, [online] 81(3–4), pp.429–450. https://doi.org/10.1007/S10472-017-9564-8/METRICS.

GANGIDI, P., 2019. A systematic approach to root cause analysis using 3 × 5 why’s technique. International Journal of Lean Six Sigma, 10(1), pp.295–310. https://doi.org/10.1108/IJLSS-10-2017-0114/FULL/XML.

HENDRASTUTY, N., RAHMAN ISNAIN, A. and YANTI RAHMADHANI, A., 2021. Analisis Sentimen Masyarakat Terhadap Program Kartu Prakerja Pada Twitter Dengan Metode Support Vector Machine. Jurnal Informatika: Jurnal Pengembangan IT, [online] 6(3), pp.150–155. https://doi.org/10.30591/JPIT.V6I3.2870.

HUSADA, H.C. and PARAMITA, A.S., 2021. Analisis Sentimen Pada Maskapai Penerbangan di Platform Twitter Menggunakan Algoritma Support Vector Machine (SVM). Teknika, [online] 10(1), pp.18–26. https://doi.org/10.34148/TEKNIKA.V10I1.311.

LESTARI, D., 2019. Pilkada DKI Jakarta 2017 : Dinamika Politik Identitas di Indonesia. JUPE : Jurnal Pendidikan Mandala, [online] 4(4), pp.12–16. https://doi.org/10.58258/JUPE.V4I4.677.

PARAMARTA, M. and DARMAWAN, J.B.B., 2023. Implementasi Metode Support Vector Machine dalam Analisis Sentimen Opini Masyarakat Terhadap Pilkada 2020 pada Media Sosial Twitter. [online] pp.836–841. Available at: <http://journal.itny.ac.id/index.php/ReTII> [Accessed 8 May 2024]

PUSPITASARI, A.M., RATNAWATI, D.E. and WIDODO, A.W., 2018. Klasifikasi Penyakit Gigi Dan Mulut Menggunakan Metode Support Vector Machine. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, [online] 2(2), pp.802–810. Available at: <https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/967> [Accessed 28 April 2024].

SARI, F.V. and WIBOWO, A., 2019. ANALISIS SENTIMEN PELANGGAN TOKO ONLINE JD.ID MENGGUNAKAN METODE NAÏVE BAYES CLASSIFIER BERBASIS KONVERSI IKON EMOSI. Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, [online] 10(2), pp.681–686. https://doi.org/10.24176/SIMET.V10I2.3487.

SINGH, V., SINGH, G., RASTOGI, P. and DESWAL, D., 2018. Sentiment analysis using lexicon based approach. PDGC 2018 - 2018 5th International Conference on Parallel, Distributed and Grid Computing, pp.13–18. https://doi.org/10.1109/PDGC.2018.8745971.

SOARES Ito, A., YLIPÄÄ, T., GULLANDER, P., BOKRANTZ, J. and SKOOGH, A., 2022. Prioritisation of root cause analysis in production disturbance management. International Journal of Quality and Reliability Management, 39(5), pp.1133–1150. https://doi.org/10.1108/IJQRM-12-2020-0402/FULL/PDF.

IKAYANTI, H., 2017. Analisis Akar Masalah (Root Cause Analysis) Kecurangan Akademik Pada Saat Ujian. Jurnal Ilmiah Mahasiswa FEB,6(1), https://jimfeb.ub.ac.id/index.php/jimfeb/article/view/4359.

SATRIA, H., 2024. Tweet-Harvest, Github [online] https://github.com/helmisatria/tweet-harvest

Diterbitkan

29-08-2025

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Analisis Sentimen Terhadap Pendapat Masyarakat Mengenai Pilkada 2024 Menggunakan Metode Support Vector Machine. (2025). Jurnal Teknologi Informasi Dan Ilmu Komputer, 12(4), 809-818. https://doi.org/10.25126/jtiik.124