Evaluating Hybrid GA-SVM Feature Selection for Indonesian Sentiment Classification Using LSTM
Keywords:
Sentiment Analysis, Indonesian Language, Genetic Algorithm, SVM, LSTM, Feature Selection, Hybrid ModelAbstract
The high dimensionality and noisy characteristics of Indonesian social media text present significant challenges for sentiment classification models. Redundant and irrelevant features may reduce classification efficiency and negatively affect model generalization performance. This study evaluates a hybrid wrapper-based feature selection approach that integrates Genetic Algorithm (GA) and Support Vector Machine (SVM) to optimize TF-IDF feature representations before classification using Long Short-Term Memory (LSTM). The experiments were conducted on 1,918 Indonesian Twitter comments related to SARS-CoV-2 sentiment, consisting of 1,044 negative and 874 positive labels. The proposed GA-SVM mechanism reduced the feature space from 35,343 to 17,931 selected features. Two evaluation scenarios were employed in this study. Under the hold-out train-test split evaluation, the GA-SVM+LSTM model achieved the best accuracy of 91.41% using a learning rate of 0.0001. Meanwhile, the 10-fold cross-validation evaluation produced an average accuracy of 89.41%, indicating stable generalization performance across different data partitions. The experimental results also show that the proposed feature selection approach improved computational efficiency by reducing training time from 263.64 seconds to 173.54 seconds. Overall, the findings indicate that hybrid GA-SVM feature selection can effectively improve TF-IDF-based sentiment classification performance for Indonesian social media text.
References
[1] K. S. Er. P. Balpreet Kaur, “SENTIMENT ANALYSIS FOR PRODUCT REVIEW,” International Research Journal of Modernization in Engineering Technology and Science, vol. 05, no. 04, pp. 4582–4592, Apr. 2023, doi: 10.56726/irjmets36776.
[2] P. Arsi, B. A. Kusuma, and A. Nurhakim, “Analisis Sentimen Pindah Ibu Kota Berbasis Naive Bayes Classifier,” Jurnal Informatika Upgris, vol. 7, no. 1, 2021, doi: 10.26877/jiu.v7i1.7636.
[3] V. Chandradev, I. M. A. D. Suarjaya, and I. P. A. Vayupati, “Analisis Sentimen Review Hotel Menggunakan Metode Deep Learning BERT,” Jurnal Buana Informatika, vol. 14, no. 2, 2023.
[4] A. Perdana, A. Hermawan, and D. Avianto, “Analisis Sentimen Terhadap Isu Penundaan Pemilu di Twitter Menggunakan Naive Bayes Clasifier,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 11, no. 2, pp. 195–200, Jul. 2022, doi: 10.32736/sisfokom.v11i2.1412.
[5] S. Jurnalis Pipin and H. Kurniawan, “Analisis Sentimen Kebijakan MBKM Berdasarkan Opini Masyarakat di Twitter Menggunakan LSTM,” Jurnal SIFO Mikroskil, vol. 23, no. 2, pp. 197–208, Oct. 2022, doi: 10.55601/jsm.v23i2.900.
[6] E. Y. Hidayat, R. W. Hardiansyah, and A. Affandy, “Analisis Sentimen Twitter untuk Menilai Opini Terhadap Perusahaan Publik Menggunakan Algoritma Deep Neural Network,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 7, no. 2, pp. 108–118, Sep. 2021, doi: 10.25077/teknosi.v7i2.2021.108-118.
[7] R. A. Pramunendar, D. P. Prabowo, and R. A. Megantara, “Metode Recurrent Neural Network (RNN) Dengan Arsitektur LSTM untuk Analisis Sentimen Opini Publik Terkait Vaksin COVID-19,” JURNAL INFORMATIKA UPGRIS, vol. 8, no. 1, pp. 44–48, Jun. 2022.
[8] S. Khomsah and A. S. Aribowo, “Text-Preprocessing Model Youtube Comments in Indonesian,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 4, no. 4, pp. 648–654, Aug. 2020, doi: 10.29207/resti.v4i4.2035.
[9] G. Angiani M. Ferrari, R. Fontanini, P. Fornacciari, E. Iotti, F. Magelli, and S. Manicardi, “A comparison between preprocessing techniques for sentiment analysis in Twitter,” in CEUR Workshop Proceedings, G. Armano, A. Bozzon, M. Cristani, and A. Giuliani, Eds., Italy: Creative Commons CC0, Sep. 2016. Accessed: Sep. 04, 2025. [Online]. Available: https://ceur-ws.org/Vol-1748/paper-06.pdf
[10] R. Setiabudi, N. M. S. Iswari, and A. Rusli, “Enhancing text classification performance by preprocessing misspelled words in Indonesian language,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 19, no. 4, pp. 1234–1241, Aug. 2021, doi: 10.12928/TELKOMNIKA.v19i4.20369.
[11] S. Khairunnisa, A. Adiwijaya, and S. Al Faraby, “Pengaruh Text Preprocessing terhadap Analisis Sentimen Komentar Masyarakat pada Media Sosial Twitter (Studi Kasus Pandemi COVID-19),” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 2, p. 406, Apr. 2021, doi: 10.30865/mib.v5i2.2835.
[12] M. Buyukkececi and M. C. Okur, “A Comprehensive Review of Feature Selection and Feature Selection Stability in Machine Learning,” 2023. doi: 10.35378/gujs.993763.
[13] H. T. Pham, J. Awange, and M. Kuhn, “Evaluation of Three Feature Dimension Reduction Techniques for Machine Learning-Based Crop Yield Prediction Models,” Sensors, vol. 22, no. 17, 2022, doi: 10.3390/s22176609.
[14] T. Karpagalingam and M. Karuppaiah, “Optimal feature subset selection based on combining document frequency and term frequency for text classification,” Computing and Informatics, vol. 39, no. 5, 2021, doi: 10.31577/CAI_2020_5_881.
[15] Siti Mutmainah, Fathir, and Erin Eka Citra, “Improving the Accuracy of Social Media Sentiment Classification with the Combination of TF-IDF Method and Random Forest Algorithm,” Journix: Journal of Informatics and Computing, vol. 1, no. 1, pp. 30–40, Apr. 2025, doi: 10.63866/journix.v1i1.2.
[16] A. Madasu and S. Elango, “Efficient feature selection techniques for sentiment analysis,” Multimed. Tools Appl., vol. 79, no. 9–10, 2020, doi: 10.1007/s11042-019-08409-z.
[17] J. Khan, A. Alam, and Y. Lee, “Intelligent Hybrid Feature Selection for Textual Sentiment Classification,” IEEE Access, vol. 9, pp. 140590–140608, 2021, doi: 10.1109/ACCESS.2021.3118982.
[18] P. H. Prastyo, I. Ardiyanto, and R. Hidayat, “A Combination of Query Expansion Ranking and GA-SVM for Improving Indonesian Sentiment Classification Performance,” Procedia Comput. Sci., vol. 189, pp. 108–115, 2021, doi: 10.1016/j.procs.2021.05.074.
[19] R. S. Sudeep K. Hase, “Hybrid Feature Selection on Social Media Dataset for Sentiment Classification using Deep Learning Techniques,” Communications on Applied Nonlinear Analysis, vol. 32, no. 9s, pp. 1899–1918, Mar. 2025, doi: 10.52783/cana.v32.4362.
[20] P. H. Prastyo, I. Ardiyanto, and R. Hidayat, “A Review of Feature Selection Techniques in Sentiment Analysis Using Filter, Wrapper, or Hybrid Methods,” in 2020 6th International Conference on Science and Technology (ICST), IEEE, Sep. 2020, pp. 1–6. doi: 10.1109/ICST50505.2020.9732885.
[21] O. M. Alyasiri, Y. N. Cheah, and A. K. Abasi, “Hybrid Filter-Wrapper Text Feature Selection Technique for Text Classification,” in International Conference on Communication and Information Technology, ICICT 2021, 2021. doi: 10.1109/ICICT52195.2021.9567898.
[22] S. Belkarkor, I. Hafidi, and M. Nachaoui, “Feature Selection for Text Classification Using Genetic Algorithm,” in Lecture Notes in Networks and Systems, vol. 656 LNNS, 2023, pp. 69–80. doi: 10.1007/978-3-031-29313-9_7.
[23] N. Azhar, P. P. Adikara, and S. Adinugroho, “Analisis Sentimen Ulasan Kedai Kopi Menggunakan Metode Naive Bayes dengan Seleksi Fitur Algoritme Genetika,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, pp. 609–618, Jun. 2021, doi: 10.25126/jtiik.2021834436.
[24] B. Ghaddar and J. Naoum-Sawaya, “High dimensional data classification and feature selection using support vector machines,” Eur. J. Oper. Res., vol. 265, no. 3, 2018, doi: 10.1016/j.ejor.2017.08.040.
[25] D. Patel, A. Saxena, and J. Wang, “A Machine Learning-Based Wrapper Method for Feature Selection,” International Journal of Data Warehousing and Mining, vol. 20, no. 1, 2024, doi: 10.4018/IJDWM.352041.
[26] C. H. Lin and U. Nuha, “Sentiment analysis of Indonesian datasets based on a hybrid deep-learning strategy,” J. Big Data, vol. 10, no. 1, 2023, doi: 10.1186/s40537-023-00782-9.
[27] S. Sarkar, S. Vinay, C. Djeddi, and J. Maiti, “Classification and pattern extraction of incidents: a deep learning-based approach,” Neural Comput. Appl., vol. 34, no. 17, 2022, doi: 10.1007/s00521-021-06780-3.
[28] N. C. Dang, M. N. Moreno-García, and F. De la Prieta, “Sentiment analysis based on deep learning: A comparative study,” Electronics (Switzerland), vol. 9, no. 3, 2020, doi: 10.3390/electronics9030483.
[29] L. Kurniasari and A. Setyanto, “Sentiment analysis using recurrent neural network-lstm in bahasa Indonesia,” Journal of Engineering Science and Technology, vol. 15, no. 5, 2020.
[30] N. Hanafiah, Y. Setiawan, A. Buntaran, and M. Reynaldi, “Sentiment Analysis of Tourism Objects on Trip Advisor Using LSTM Method,” Journal of Computer Science and Technology Studies, vol. 4, no. 2, 2022, doi: 10.32996/jcsts.2022.4.2.1.
[31] T. Crippa Praha and M. Nugraheni, “Indonesian Fake News Classification Using Transfer Learning in CNN and LSTM,” Indonesia, Sep. 2024. doi: http://dx.doi.org/10.62527/joiv.8.2.2126.
[32] S. Mujilahwati, N. Z. Mohd Safar, K. M. N. Ku Khalif, and N. Ghazalli, “Optimizing Sentiment Analysis of Indonesian Texts: Enhancing Deep Learning Models with Genetic Algorithm-Based Feature Selection,” Journal of Soft Computing and Data Mining, vol. 5, no. 2, Dec. 2024, doi: 10.30880/jscdm.2024.05.02.016.
[33] M. T. Razaq, D. Nurjanah, and H. Nurrahmi, “Analisis Sentimen Review Film Menggunakan Naive Bayes Classifier dengan Fitur TF-IDF,” e-Proceeding of Engineering, vol. 10, no. 2, 2023.
[34] A. Aziz, “Analisis Sentimen Identifikasi Opini Terhadap Produk, Layanan dan Kebijakan Perusahaan Menggunakan Algoritma TF-IDF dan SentiStrength,” 2022.
[35] D. Sugiarto, E. Utami, and A. Yaqin, “Perbandingan Kinerja Model TF-IDF dan BOW untuk Klasifikasi Opini Publik Tentang Kebijakan BLT Minyak Goreng,” Jurnal Teknik Industri , vol. 12, no. 3, 2022.
[36] F. C. Zegarra, J. Vargas-Machuca, and A. M. Coronado, “A COMPARATIVE STUDY OF CNN, LSTM, BiLSTM, AND GRU ARCHITECTURES FOR TOOL WEAR PREDICTION IN MILLING PROCESSES,” Journal of Machine Engineering, vol. 23, no. 4, 2023, doi: 10.36897/jme/174019.
[37] V. R. Prasetyo, M. F. Naufal, and K. Wijaya, “Sentiment Analysis of ChatGPT on Indonesian Text using Hybrid CNN and Bi-LSTM,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 2, pp. 327–333, Apr. 2025, doi: 10.29207/resti.v9i2.6334.
[38] N. M. G. Dwi Purnamasari, M. A. Fauzi, I. Indriati, and L. S. Dewi, “Cyberbullying identification in twitter using support vector machine and information gain based feature selection,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 18, no. 3, p. 1494, Jun. 2020, doi: 10.11591/ijeecs.v18.i3.pp1494-1500.
[39] E. Hokijuliandy, H. Napitupulu, and F. Firdaniza, “Analisis Sentimen Menggunakan Metode Klasifikasi Support Vector Machine (SVM) dan Seleksi Fitur Chi-Square,” SisInfo : Jurnal Sistem Informasi dan Informatika, vol. 5, no. 2, 2023, doi: 10.37278/sisinfo.v5i2.670.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Siti Mujilahwati, Noor Zuraidin bin Mohd Safar
This work is licensed under a Creative Commons Attribution 4.0 International License.
JUITA: Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.
