Analisis Sentimen Pengguna Twitter Mengenai Kotak Kosong di Pilkada Indonesia Tahun 2024 Menggunakan Algoritma LSTM
DOI:
https://doi.org/10.34010/komputika.v14i2.16976Abstract
Fenomena kotak kosong dalam Pilkada 2024 menjadi perbincangan ramai di Twitter, memunculkan pandangan pro dan kontra di masyarakat mengenai keberadaan calon tunggal yang dinilai berpotensi memengaruhi stabilitas politik di daerah. Diskusi publik di media sosial umumnya menggunakan bahasa informal, dialek bahasa daerah, serta tidak mengikuti kaidah baku, sehingga menyulitkan analisis manual dan berisiko menimbulkan bias. Maka dari itu, penelitian ini mengimplementasikan pendekatan deep learning dengan memanfaatkan model Long Short-Term Memory (LSTM) dan word embedding GloVe. Proses pelabelan dilakukan secara otomatis menggunakan Indonesia Sentiment Lexicon (INSET) untuk mengklasifikasikan sentimen masyarakat terhadap kebijakan kotak kosong berdasarkan data Twitter. Data penelitian terdiri dari 2.168 tweet yang diperoleh melalui teknik crawling, kemudian dievaluasi menggunakan metode 10-fold cross-validation. Analisis sentimen menghasilkan distribusi opini publik, yaitu 35,9% negatif, 32,8% positif, dan 31,3% netral. Hasil pengujian menunjukkan akurasi tertinggi sebesar 94,93% pada fold ke-6, dengan rata-rata akurasi keseluruhan mencapai 90,08%. Penelitian ini berkontribusi dalam pengembangan sistem analisis berbasis deep learning untuk pemantauan opini publik, serta menunjukkan potensi data media sosial sebagai sumber informasi strategis dalam memahami persepsi masyarakat terhadap fenomena politik.
References
[1] S. Sarbaini, “Penyelenggaraan Pemilihan Kepala Daerah Secara Langsung dan Demokratis Sebagai Bentuk Perwujudan Hak Asasi Politik Masyarakat di Indonesia,” Legalitas: Jurnal Hukum, vol. 12, no. 1, p. 107, Jun. 2020, doi: 10.33087/legalitas.v12i1.197.
[2] A. Budiman, “PILKADA PASLON TUNGGAL, KINERJA PARTAI POLITIK, DAN MASA DEPAN DEMOKRASI DI INDONESIA,” 2018.
[3] Simon Kemp, “Digital 2023: Indonesia,” www.datareportal.com.
[4] M. Athoillah and R. K. Putri, “Utilizing Support Vector Machines to Detect Hate Speech on Social Media,” Science, Engineering and Technology, vol. 4, no. 2, pp. 53–60, Sep. 2024, doi: 10.54327/set2024/v4.i2.129.
[5] R. Kusumaningrum, I. Z. Nisa, R. P. Nawangsari, and A. Wibowo, “Sentiment analysis of Indonesian hotel reviews: from classical machine learning to deep learning,” International Journal of Advances in Intelligent Informatics, vol. 7, no. 3, pp. 292–303, Nov. 2021, doi: 10.26555/ijain.v7i3.737.
[6] B. Jang, M. Kim, G. Harerimana, S. U. Kang, and J. W. Kim, “Bi-LSTM model to increase accuracy in text classification: Combining word2vec CNN and attention mechanism,” Applied Sciences (Switzerland), vol. 10, no. 17, Sep. 2020, doi: 10.3390/app10175841.
[7] Kusum and S. P. Panda, “Sentiment analysis using global vector and long short-term memory,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 26, no. [1] S. Sarbaini, “Penyelenggaraan Pemilihan Kepala Daerah Secara Langsung dan Demokratis Sebagai Bentuk Perwujudan Hak Asasi Politik Masyarakat di Indonesia,” Legalitas: Jurnal Hukum, vol. 12, no. 1, p. 107, Jun. 2020, doi: 10.33087/legalitas.v12i1.197.
[2] A. Budiman, “PILKADA PASLON TUNGGAL, KINERJA PARTAI POLITIK, DAN MASA DEPAN DEMOKRASI DI INDONESIA,” 2018.
[3] Simon Kemp, “Digital 2023: Indonesia,” www.datareportal.com.
[4] M. Athoillah and R. K. Putri, “Utilizing Support Vector Machines to Detect Hate Speech on Social Media,” Science, Engineering and Technology, vol. 4, no. 2, pp. 53–60, Sep. 2024, doi: 10.54327/set2024/v4.i2.129.
[5] R. Kusumaningrum, I. Z. Nisa, R. P. Nawangsari, and A. Wibowo, “Sentiment analysis of Indonesian hotel reviews: from classical machine learning to deep learning,” International Journal of Advances in Intelligent Informatics, vol. 7, no. 3, pp. 292–303, Nov. 2021, doi: 10.26555/ijain.v7i3.737.
[6] B. Jang, M. Kim, G. Harerimana, S. U. Kang, and J. W. Kim, “Bi-LSTM model to increase accuracy in text classification: Combining word2vec CNN and attention mechanism,” Applied Sciences (Switzerland), vol. 10, no. 17, Sep. 2020, doi: 10.3390/app10175841.
[7] Kusum and S. P. Panda, “Sentiment analysis using global vector and long short-term memory,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 26, no. 1, pp. 414–422, Apr. 2022, doi: 10.11591/ijeecs.v26.i1.pp414-422.
[8] A. Rao and N. Spasojevic, “Actionable and Political Text Classification using Word Embeddings and LSTM,” Jul. 2016, [Online]. Available: http://arxiv.org/abs/1607.02501
[9] Xianghua Fu, Jingying Yang, Jianqiang Li, Min Fang, and Huihui Wang, “Lexicon-Enhanced LSTM With Attention for General Sentiment Analysis,” IEEE, vol. 6, Oct. 2018.
[10] A. Nilsen, “Perbandingan Model RNN, Model LSTM, dan Model GRU dalam Memprediksi Harga Saham-Saham LQ45,” Jurnal Statistika dan Aplikasinya, vol. 6, no. 1, 2022.
[11] Safwan Mahmood Al-Selwi et al., “RNN-LSTM: From applications to modeling techniques and beyond—Systematic review,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 5, Jun. 2024.
[12] X. Wu, B. Xiang, H. Lu, C. Li, X. Huang, and W. Huang, “Optimizing Recurrent Neural Networks: A Study on Gradient Normalization of Weights for Enhanced Training Efficiency,” Applied Sciences (Switzerland), vol. 14, no. 15, Aug. 2024, doi: 10.3390/app14156578.
[13] Palash Goyal, Sumit Pandey, and Karan Jain, Deep Learning for Natural Language Processing: Creating Neural Networks with Python. Bangalore: apress, 2018.
[14] A. A. Winoto and A. F. V. Roy, “Model of Predicting the Rating of Bridge Conditions in Indonesia with Regression and K-Fold Cross Validation,” International Journal of Sustainable Construction Engineering and Technology, vol. 14, no. 1, pp. 249–259, Feb. 2023, doi: 10.30880/ijscet.2023.14.01.022.
[15] D. S. Soper, “Greed is good: Rapid hyperparameter optimization and model selection using greedy k-fold cross validation,” Electronics (Switzerland), vol. 10, no. 16, Aug. 2021, doi: 10.3390/electronics10161973.
[16] IRFAN HANIF, “KLASIFIKASI PERINTAH BAHASA NATURAL MENGGUNAKAN GLOBAL VECTORS FOR WORD REPRESENTATIONS (GLOVE), CONVOLUTIONAL NEURAL NETWORKS, DAN TEKNIK TRANSFER LEARNING PADA APLIKASI CHATBOTS,” Institut Teknologi Sepuluh Nopember, Surabaya, 2018.
