Analisis Sentimen Masyarakat terhadap Kebijakan Gubernur Jawa Barat di Sosial Media menggunakan Algoritma Long Short Term Memory

M Fikri Setiawan; Elvi Rahmi

doi:10.31004/riggs.v5i2.11497

Authors

M Fikri Setiawan Politeknik Negeri Bengkalis
Elvi Rahmi Politeknik Negeri Bengkalis

DOI:

https://doi.org/10.31004/riggs.v5i2.11497

Keywords:

Analisis Sentimen, LSTM, Kebijakan Gubernur Jawa Barat, Media Sosial

Abstract

Penelitian ini bertujuan menganalisis sentimen masyarakat terhadap kebijakan Gubernur Jawa Barat yang terekam pada berbagai media sosial, seperti Twitter, Instagram, dan TikTok, dengan memanfaatkan algoritma Long Short-Term Memory (LSTM). Analisis sentimen dipilih karena mampu memberikan gambaran mengenai persepsi publik secara cepat dan berkelanjutan seiring meningkatnya penggunaan media sosial sebagai sarana penyampaian opini. Permasalahan utama penelitian ini adalah karakteristik opini masyarakat yang sangat dinamis, berjumlah besar, serta tersebar di berbagai platform digital, sehingga metode konvensional seperti survei atau wawancara memiliki keterbatasan dalam memperoleh informasi secara real time dan representatif. Dataset penelitian diperoleh melalui proses scrapping komentar berbahasa Indonesia yang berkaitan dengan kebijakan Gubernur Jawa Barat. Data kemudian diproses menggunakan tahapan Knowledge Discovery in Databases (KDD) yang meliputi seleksi data, preprocessing, transformasi data, pelabelan sentimen, serta pembobotan kata menggunakan metode Word Embedding untuk menghasilkan representasi fitur yang optimal. Selanjutnya, model LSTM dilatih untuk mengklasifikasikan sentimen ke dalam tiga kategori, yaitu positif, negatif, dan netral. Evaluasi performa model dilakukan menggunakan metrik akurasi, precision, recall, dan F1-score guna mengukur kemampuan klasifikasi secara menyeluruh. Hasil penelitian menunjukkan bahwa algoritma LSTM mampu mengidentifikasi dan mengklasifikasikan sentimen masyarakat dengan tingkat performa yang baik, sehingga dapat menggambarkan kecenderungan opini publik terhadap berbagai kebijakan yang diterapkan. Temuan ini diharapkan dapat menjadi landasan dalam pengembangan sistem pemantauan opini publik berbasis kecerdasan buatan yang mendukung proses evaluasi kebijakan serta pengambilan keputusan pemerintah daerah secara lebih cepat, responsif, objektif, dan tepat sasaran

Downloads

Download data is not yet available.

References

[1] Kementerian PANRB, 'Pedoman Standar Penyusunan Survei Kepuasan Masyarakat,' 2017.

[2] Tirto.id, 'Wagub DIY Raih Indeks Kepuasan Warga Tertinggi Sepulau Jawa,' 28 Mei 2025.

[3] A. Ceron, L. Curini, and S. M. Iacus, 'Using sentiment analysis to monitor electoral campaigns: Method matters—evidence from the United States and Italy,' Social Science Computer Review, vol. 33, no. 1, pp. 3–20, 2015.

[4] I. Mergel, 'Social media adoption and resulting tactics in the US federal government,' Government Information Quarterly, vol. 30, no. 2, pp. 123–130, 2013.

[5] S. Stieglitz and L. Dang-Xuan, 'Emotions and information diffusion in social media—sentiment of microblogs and sharing behavior,' Journal of Management Information Systems, vol. 29, no. 4, pp. 217–248, 2013.

[6] Y. Bae and H. Lee, 'Sentiment analysis of Twitter audiences: Measuring the positive or negative influence of popular twitterers,' J. Assoc. Inf. Sci. Technol., vol. 63, no. 12, pp. 2521–2535, 2012.

[7] Asosiasi Penyelenggara Jasa Internet Indonesia (APJII), Laporan Survei Internet APJII 2024. Jakarta, Indonesia: APJII, 2024.

[8] We Are Social and Meltwater, Digital 2024: Indonesia. London, UK: We Are Social, 2024.

[9] Badan Pusat Statistik Provinsi Jawa Barat, Provinsi Jawa Barat Dalam Angka 2023. Bandung, Indonesia: BPS Jawa Barat, 2023.

[10] Badan Pusat Statistik, Produk Domestik Regional Bruto Menurut Provinsi 2019–2023. Jakarta, Indonesia: BPS, 2024.

[11] Dinas Kebudayaan dan Pariwisata Jawa Barat, Profil Kebudayaan Provinsi Jawa Barat 2023. Bandung, Indonesia: Disbudpar Jabar, 2023.

[12] S. Stieglitz and L. Dang-Xuan, “Emotions and information diffusion in social media—Sentiment of microblogs and sharing behavior,” J. Manage. Inf. Syst., vol. 29, no. 4, pp. 217–248, 2013.

[13] M. A. Fauzi and R. P. Utomo, “Analisis sentimen pada media sosial menggunakan metode Naïve Bayes dan Support Vector Machine,” J. Teknol. Inf. dan Ilmu Komput., vol. 6, no. 4, pp. 401–408, 2019.

[14] R. Kurniawan and D. K. Dewi, “Analisis sentimen terhadap kebijakan pemerintah pada Twitter menggunakan metode SVM,” J. Edukasi dan Penelitian Informatika (JEPIN), vol. 5, no. 2, pp. 217–224, 2019.

[15] M. C. Farsiah, "Analisis Sentimen Menggunakan Arsitektur LSTM Terhadap Fenomena Citayam Fashion Week," 2023.

[16] A. Kustiwa, A. F. Akbar, and A. Pinandito, "Studi Perbandingan CNN-LSTM dan LSTM dalam Mendeteksi Emosi pada Data Teks," 2022.

[17] Y. A. Pradana, I. Cholissodin, and D. Kurnianingtyas, "Analisis Sentimen Pemindahan Ibu Kota Indonesia menggunakan LSTM dan Word2Vec," 2022.

[18] M. N. I. Sina and E. B. Setiawan, "Stock Price Correlation Analysis with Twitter Sentiment Using CNN-LSTM," 2023.

[19] S. F. Handayani, R. W. Pratiwi, Dairoh, and D. I. Af’idah, "Analisis Sentimen pada Ulasan Twitter dengan LSTM," 2021.

[20] M. F. Naufal and S. F. Kusuma, "Analisis Sentimen Twitter terhadap Kebijakan PPKM," 2022.

[21] D. A. Firdlous and R. Andrian, "Sentiment Analysis Public Twitter on 2024 Election using LSTM," 2024.

[22] P. H. Prastyo, M. A. Ridho, and S. A. Wibowo, "Sentiment Analysis on COVID-19 Using SVM," 2021.

[23] C.-H. Lin and U. Nuha, "Sentiment Analysis of Indonesian Datasets Based on Hybrid Deep Learning Strategy," 2023.

[24] P. R. A. Savitri, I. M. A. D. Suarjaya, and W. O. Vihikan, "Sentiment Analysis on Korean Culture in Indonesia," 2022.

[25] A. Hermida, “Twittering the news: The emergence of ambient journalism,” Journalism Practice, vol. 4, no. 3, pp. 297–308, 2010

[26] A. Hu, L. Zhao, and S. Huang, “Understanding User Engagement on Instagram: A Case Study of Social Movements,” International Journal of Communication, vol. 14, pp. 4534–4556, 2020.

[27] J. A. Chewning and A. M. Doerfel, “Twitter and health policy: Using a network approach to explore information flow about the Affordable Care Act,” Communication Studies, vol. 64, no. 5, pp. 451–468, 2013.

[28] D. M. Boyd and N. B. Ellison, “Social network sites: Definition, history, and scholarship,” J. Comput.-Mediat. Commun., vol. 13, no. 1, pp. 210–230, 2007.

[29] A. M. Kaplan and M. Haenlein, “Users of the world, unite! The challenges and opportunities of Social Media,” Business Horizons, vol. 53, no. 1, pp. 59–68, Jan. 2010.

[30] B. Liu, “Sentiment Analysis and Opinion Mining”. San Rafael, CA: Morgan & Claypool, 2012.

[31] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” *Neural Computation*, vol. 9, no. 8, pp. 1735–1780, 1997.

[33] F. A. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget: Continual prediction with LSTM," Neural computation, vol. 12, no. 10, pp. 2451-2471, 2000.

[34] Y. Wang, M. Huang, X. Zhu, and L. Zhao, "Attention-based LSTM for aspect-level sentiment classification," in Proceedings of the 2016 conference on empirical methods in natural language processing, 2016, pp. 606-615.

[35] X. Wang, W. Jiang, and Z. Luo, "Combination of convolutional and recurrent neural network for sentiment analysis of short texts," in Proceedings of COLING 2016, the 26th international conference on computational linguistics: technical papers, 2016, pp. 2428-2437.

[36] D. Jurafsky and J. H. Martin, Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 3rd ed. London: Pearson Education, 2020.

[37] C. D. Manning and H. Schütze, Foundations of statistical natural language processing. Cambridge: MIT Press, 2019.

[38] S. Bird, E. Klein, and E. Loper, Natural language processing with Python: analyzing text with the natural language toolkit. Sebastopol: O'Reilly Media, 2019.

[39] T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv:1301.3781, 2013.

[40] J. S. Dryzek, "Deliberative democracy and beyond: liberals, critics, contestations," Political Studies, vol. 50, no. 1, pp. 1-18, 2002.

[41] S. Grimmelikhuijsen and A. Meijer, "Effects of transparency on the perceived trustworthiness of a government organization: Evidence from an online experiment," Journal of Public Administration Research and Th7eory, vol. 24, no. 1, pp. 137-157, 2014.

[42] Kurniawati, T. R., “Analisis Big Data dalam Pengambilan Kebijakan Publik di Indonesia,” Jurnal Ilmu Administrasi Negara, vol. 10, no. 2, pp. 35–46, 2023.

[43] J. Bhandari and S. Bimo, “TikTok and the Public Sphere: Short Video Platforms as New Spaces for Civic Participation,” New Media & Society, vol. 25, no. 1, pp. 23–41, 2023.