Hybrid Deep Learning Models for Multilingual Sentiment Analysis in Low-Resource Languages
DOI:
https://doi.org/10.25181/coding.v1i1.4306Keywords:
BiLSTM, CNN, Deep Learning, Multilingual: low-resource languages, Sentiment AnalysisAbstract
Multilingual sentiment analysis remains challenging, especially for low-resource languages with limited annotated data and linguistic tools. This study proposes a hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM), enhanced with mBERT embeddings. The model is trained and tested on a multilingual dataset covering ten languages, including Swahili, Hausa, Yoruba, and Indonesian. Results show the model achieved 84.3% accuracy and a macro F1-score of 83.1%, outperforming baseline models such as Naive Bayes and standalone BiLSTM. The hybrid architecture effectively captures both local and contextual sentiment cues across different languages. While Indonesians scored highest due to more abundant training data, the model also performed consistently in low-resource settings. These findings suggest that combining multilingual embeddings with hybrid architectures offers a promising approach for sentiment analysis in linguistically diverse environments.
Downloads
References
Ardiansyah, A., Argarini Pratama, E., Imam Fadlilah, N., & Bina Sarana Informatika, U. (2024). Analisis Sentimen Pengguna Terhadap Aplikasi ChatGPT Di Google Play Store: Penerapan Algoritma Support Vector Machine. 11(2), 247–254.
Efraim, D. A. (2023). Analisis Sentimen Pada Sosial Media Instagram Menggunakan Algoritma Naive Bayes ( Studi Kasus : Timnas Futsal Indonesia ). April 2012, 498–509.
Fauzi, A., Akbar, M. F., & Asmawan, Y. F. A. (2019). Sentimen Analisis Berinternet Pada Media Sosial dengan Menggunakan Algoritma Bayes. Jurnal Informatika, 6(1), 77–83. https://doi.org/10.31311/ji.v6i1.5437
Iin, I., Supriatna, R., Mulyawan, M., & Rohman, D. (2024). Penerapan Natural Language Processing Dalam Analisis Sentimen Cawapres 2024 Menggunakan Algoritma Naive Bayes. JATI (Jurnal Mahasiswa Teknik Informatika), 8(1), 1109–1115. https://doi.org/10.36040/jati.v8i1.8572
Intan, S. F., Permana, I., Salisah, F. N., Afdal, M., & Muttakin, F. (2023). Perbandingan Algoritma KNN, NBC, dan SVM: Analisis Sentimen Masyarakat Terhadap Perparkiran di Kota Pekanbaru. JUSIFO (Jurnal Sistem Informasi), 9(2), 85–96. https://doi.org/10.19109/jusifo.v9i2.21357
Jain, T. I., & Nemade, D. (2010). Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis. International Journal of Computer Applications, 7(5), 12–21. https://doi.org/10.5120/1160-1453
Lutfina, E., Andriana, W., Quamila, S., Wiratmaja, P., & Febrianti, E. (2024). Science, Technology and Management Journal Metode dan Algoritma Dalam Sentimen Analisis: Systematic Literature Review Info Artikel. 4(2), 67–79. http://journal.unkartur.ac.id/index.php/stmj
Mailoa, F. F. (2021). Analisis sentimen data twitter menggunakan metode text mining tentang masalah obesitas di indonesia. Journal of Information Systems for Public Health, 6(1), 44. https://doi.org/10.22146/jisph.44455
Maulana, I., Apriandari, W., & Pambudi, A. (2023). Analisis Sentimen Berbasis Aspek Terhadap Ulasan Aplikasi Mypertamina Menggunakan Support Vector Machine. IDEALIS : InDonEsiA JournaL Information System, 6(2), 172–181. https://doi.org/10.36080/idealis.v6i2.3022
Maulana, M. A., Setyanto, A., & Kurniawan, M. P. (2018). Analisis Sentimen media Sosial Universitas Amikom Yogyakarta Sebagai Sarana Penyebaran Informasi Menggunakan Algoritma Klasifikasi Svm. Seminar Nasional Teknologi Informasi Dan Multimedia 2018 UNIVERSITAS AMIKOM Yogyakarta, 10 Februari 2018, 7–12.
Maulana, R., Voutama, A., & Ridwan, T. (2023). Analisis Sentimen Ulasan Aplikasi MyPertamina pada Google Play Store menggunakan Algoritma NBC. Jurnal Teknologi Terpadu, 9(1), 42–48. https://doi.org/10.54914/jtt.v9i1.609
Normah, Rifai, B., Vambudi, S., & Maulana, R. (2022). Analisa Sentimen Perkembangan Vtuber Dengan Metode Support Vector Machine Berbasis SMOTE. Jurnal Teknik Komputer AMIK BSI, 8(2), 174–180. https://doi.org/10.31294/jtk.v4i2
Pahtoni, T. Y., & Jati, H. (2024). Analisis Sentimen Data Twitter Terkait Chatgpt Menggunakan Orange Data Mining. Jurnal Teknologi Informasi Dan Ilmu Komputer, 11(2), 329–336. https://doi.org/10.25126/jtiik.20241127276
Pak, A., & Paroubek, P. (2010). Twitter as a corpus for sentiment analysis and opinion mining. Proceedings of the 7th International Conference on Language Resources and Evaluation, LREC 2010, 1320–1326. https://doi.org/10.17148/ijarcce.2016.51274
Pratama, M. Y., Putri, U. A., Angraini, P. A. D., Puspita, D., & Kurniawan, F. (2023). Analisis Sentimen Chat GPT sebagai Masa Depan Pekerja pada Media Sosial Youtube menggunakan Algoritma Klasifikasi Naive Bayes. Explore: Jurnal Sistem Informasi Dan Telematika, 14(2), 193. https://doi.org/10.36448/jsit.v14i2.3391
Putranti, N. D., & Winarko, E. (2014). Analisis Sentimen Twitter untuk Teks Berbahasa Indonesia dengan Maximum Entropy dan Support Vector Machine. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 8(1), 91. https://doi.org/10.22146/ijccs.3499
Ramadhani, B., & Suryono, R. R. (2024). Komparasi Algoritma Naïve Bayes dan Logistic Regression Untuk Analisis Sentimen Metaverse. Jurnal Media Informatika Budidarma, 8(2), 714. https://doi.org/10.30865/mib.v8i2.7458
Winoto, D., Desta Aditia, V., Sorisa, C., Priskila, R., & Handrianus Pranatawijaya, V. (2024). Analisis Sentimen Pada Ulasan Pengguna Terhadap Aplikasi Pembelajaran Bahasa Duolingo: Menggunakan Algoritma Naïve Bayes Dan K-Nearest Neighbor. JATI (Jurnal Mahasiswa Teknik Informatika), 8(3), 3230–3236. https://doi.org/10.36040/jati.v8i3.9647
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Coding: Journal of Computing and Software Engineering
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
