Journal of Government and Civil Society

Articles

Vol. 9 No. 2 (2025): Journal of Government and Civil Society (October)

Deep Learning-Based Sentiment Analysis of Twitter Discourse on the Gaza and Ukraine Conflicts Using Bi-GRU Architecture

DOI:
https://doi.org/10.31000/jgcs.v9i2.14288
Submitted
24 June 2025
Published
30 October 2025

Abstract

The proliferation of social media has transformed platforms like Twitter into dynamic arenas for expressing public sentiment during geopolitical crises. This study examines global public opinion on the Gaza and Ukraine conflicts by employing a deep learning-based sentiment analysis model utilizing a Bidirectional Gated Recurrent Unit (Bi-GRU) architecture. A total of 24,177 tweets were collected and pre-processed, followed by sentiment labeling using a hybrid lexical approach that combines VADER and TextBlob. Feature extraction was conducted using the TF-IDF method, and the Bi-GRU model was trained and evaluated using standard performance metrics. The model achieved an accuracy of 88.06% and an average F1-score of 85.07%, demonstrating superior performance in recognizing sentiment, especially for negative expressions. Word cloud analysis further revealed the dominance of emotionally charged terms such as "genocide" and "pray for Gaza," indicating the strong affective orientation of online discourse. The study confirms the efficacy of Bi-GRU in handling informal and contextually complex texts. It highlights the role of social media in articulating collective emotions and shaping public narratives during conflict. These findings offer methodological contributions to the field of natural language processing and practical implications for real-time crisis monitoring, policymaking, and humanitarian communication strategies.

Proliferasi media sosial telah mengubah platform seperti Twitter menjadi arena dinamis untuk mengekspresikan sentimen publik selama krisis geopolitik. Studi ini meneliti opini publik global terhadap konflik Gaza dan Ukraina dengan menggunakan model analisis sentimen berbasis pembelajaran mendalam yang memanfaatkan arsitektur Bidirectional Gated Recurrent Unit (Bi-GRU). Sebanyak 24.177 tweet dikumpulkan dan diproses terlebih dahulu, kemudian diberi label sentimen menggunakan pendekatan leksikal hibrida yang menggabungkan VADER dan TextBlob. Ekstraksi fitur dilakukan menggunakan metode TF-IDF, dan model Bi-GRU dilatih serta dievaluasi menggunakan metrik kinerja standar. Model ini mencapai akurasi sebesar 88,06% dan rata-rata skor F1 sebesar 85,07%, menunjukkan performa unggul dalam mengenali sentimen, terutama untuk ekspresi negatif. Analisis word cloud lebih lanjut mengungkap dominasi istilah bermuatan emosional seperti "genocide" dan "pray for Gaza", yang menunjukkan orientasi afektif yang kuat dalam wacana daring. Studi ini menegaskan efektivitas Bi-GRU dalam menangani teks informal dan kontekstual yang kompleks, serta menyoroti peran media sosial dalam mengartikulasikan emosi kolektif dan membentuk narasi publik selama konflik. Temuan ini memberikan kontribusi metodologis bagi bidang pemrosesan bahasa alami serta implikasi praktis bagi pemantauan krisis secara waktu nyata, pembuatan kebijakan, dan strategi komunikasi kemanusiaan

References

  1. An, L., Dias, D., Carvajal, C., Peyras, L., Breul, P., Jenck, O., & Guo, X. (2024). Pore Water Pressure Prediction Based on Machine Learning Methods—Application to an Earth Dam Case. Applied Sciences, 14(11), 4749. https://doi.org/10.3390/app14114749
  2. Arun, K. and Srinagesh, A. (2020). Multilingual twitter sentiment analysis using machine learning. International Journal of Electrical and Computer Engineering (Ijece), 10(6), 5992. https://doi.org/10.11591/ijece.v10i6.pp5992-6000
  3. Bashir, S., Bano, S., Shueb, S., Gul, S., Mir, A. A., Ashraf, R., Shakeela, & Noor, N. (2021). Twitter chirps for Syrian people: Sentiment analysis of tweets related to Syria Chemical Attack. International Journal of Disaster Risk Reduction, 62, 102397. https://doi.org/10.1016/j.ijdrr.2021.102397
  4. Bhat, S. (2024). Emotion Classification in Short English Texts using Deep Learning Techniques. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2402.16034
  5. Bhuvaneswari, A., Thomas, J. T. J., & Kesavan, P. (2019). Embedded Bi-directional GRU and LSTMLearning Models to Predict Disasterson Twitter Data. Procedia Computer Science, 165, 511. https://doi.org/10.1016/j.procs.2020.01.020
  6. Biswas, S., Young, K. M., & Griffith, J. (2022). A Comparison of Automatic Labelling Approaches for Sentiment Analysis. Proceedings of the 11th International Conference on Data Science, Technology and Applications DATA, Volume 1, 312-319. https://doi.org/10.5220/0011265900003269
  7. Chandra, S., Sarkar, R., Islam, S., Nandi, S., Banerjee, A., & Chatterjee, K. (2021). Sentiment Analysis on Twitter Data: A Comparative Approach. International Journal of Computer Science and Mobile Applications, 9(10), 1-12. https://doi.org/10.47760/ijcsma.2021.v09i10.001
  8. Chang, C., Hui, J. C. K., Justus-Smith, C., & Wang, T. (2024). Navigating STEM careers with AI mentors: a new IDP journey. Frontiers in Artificial Intelligence, 7. https://doi.org/10.3389/frai.2024.1461137
  9. Dang, C. N., GarcıÌa, M. N. M., & Prieta, F. D. la. (2020). Sentiment Analysis Based on Deep Learning: A Comparative Study. Electronics, 9(3), 483. https://doi.org/10.3390/electronics9030483
  10. Fayyad, M., Kurniawan, V., Anugrah, M., Estanto, B., & Bilal, T. (2024). Application of Recurrent Neural Network Bi-Long Short-Term Memory, Gated Recurrent Unit and Bi-Gated Recurrent Unit for Forecasting Rupiah Against Dollar (USD) Exchange Rate. PREDATECS, 2(1), 1-10. https://doi.org/10.57152/predatecs.v2i1.1094
  11. Habermas, J. (1989). The structural transformation of the public sphere: An inquiry into a category of bourgeois society. MIT Press. https://doi.org/10.7551/mitpress/6279.001.0001
  12. Hameed, R., Abed, W., & Sadiq, A. (2023). Evaluation of Hotel Performance with Sentiment Analysis by Deep Learning Techniques. International Journal of Interactive Mobile Technologies (Ijim), 17(09), 70-87. https://doi.org/10.3991/ijim.v17i09.38755
  13. Hong, J. (2022). Vibration Prediction of Flying IoT Based on LSTM and GRU. Electronics, 11(7), 1052. https://doi.org/10.3390/electronics11071052
  14. Hu, G., Sun, M., & Zhang, C. (2025). A high-accuracy advanced persistent threat detection model: Integrating convolutional neural networks with Kepler-optimized bidirectional gated recurrent units. Electronics, 14(9), 1772. https://doi.org/10.3390/electronics14091772
  15. Iosifov, I. (2023). COMPLEX METHOD FOR AUTOMATIC RECOGNITION OF NATURAL LANGUAGE AND EMOTIONAL STATE. Cybersecurity Education Science Technique, 3(19), 146. https://doi.org/10.28925/2663-4023.2023.19.146164
  16. Jiang, D., Zhuo, J., Fan, P., Ding, F., Hao, M., Chen, S., Dong, J., & Wu, J. F. (2025). Assessing the transformation of armed conflict types: A dynamic approach. Big Data and Cognitive Computing, 9(5), 123. https://doi.org/10.3390/bdcc9050123
  17. Jo, H., Moon, Y., Kim, J. I., & Ryu, J. L. (2016). Re-presenting a Story by Emotional Factors using Sentimental Analysis Method. arXiv (Cornell University). https://doi.org/10.48550/arXiv.1607.03707
  18. Kavitha, S. and Chinnaiah, K. (2024). Soil nutrient prediction for paddy cultivation via soil fertility and pH trained hybrid architecture: Recommendations based on nutrient deficiency. Intelligent Decision Technologies, 18(2), 685-703. https://doi.org/10.3233/idt-240423
  19. Keck, M. E., & Sikkink, K. (1998). Activists beyond borders: Advocacy networks in international politics. Cornell University Press. https://doi.org/10.7591/9781501724214
  20. Kruspe, A., Niu, J., Stillman, M., & Seeberger, P. (2024). A Dataset of Open Source Intelligence (OSINT) Tweets about the Russo-Ukrainian War. 21st International ISCRAM Conference, University of Münster, Germany: Embracing the Crisis Management Lifecycle. https://doi.org/10.59297/377r3945
  21. Kula, S., Kozik, R., & ChoraÅ›, M. (2021). Implementation of the BERT-derived architectures to tackle disinformation challenges. Neural Computing and Applications, 34(23), 20449. https://doi.org/10.1007/s00521-021-06276-0
  22. Lee, J. and Hong, J. (2022). Comparative Performance Analysis of Vibration Prediction Using RNN Techniques. Electronics, 11(21), 3619. https://doi.org/10.3390/electronics11213619
  23. Li, S., & Sun, X. (2023). Application of public emotion feature extraction algorithm based on social media communication in public opinion analysis of natural disasters. PeerJ Computer Science, 9. https://doi.org/10.7717/peerj-cs.1417
  24. Lu, X., & Zhang, H. (2021). Sentiment Analysis Method of Network Text Based on Improved AT-BiGRU Model. Scientific Programming, 2021, 1. https://doi.org/10.1155/2021/6669664
  25. Lucić, D., Katalinić, J., & Dokman, T. (2021). Sentiment Analysis of the Syrian Conflict on Twitter. Medijske Studije, 11(22), 46-61. https://doi.org/10.20901/ms.11.22.3
  26. Nimbhore, P., Tiwari, R., Hazra, T., & Yadav, M. (2024). Classification of cotton crop disease using hybrid model and MDFC feature extraction method. Journal of Phytopathology, 172(4). https://doi.org/10.1111/jph.13324
  27. Ningsih, A. K., & Hadiana, A. (2021). Disaster Tweets Classification in Disaster Response using Bidirectional Encoder Representations from Transformer (BERT). IOP Conference Series Materials Science and Engineering, 1115(1), 12032. https://doi.org/10.1088/1757-899x/1115/1/012032
  28. Omara, E., Mosa, M., & Ismail, N. (2022). Applying Recurrent Networks For Arabic Sentiment Analysis. Menoufia Journal of Electronic Engineering Research, 31(1), 21-28. https://doi.org/10.21608/mjeer.2022.218776
  29. Sasikumar, U., Zaman, A. N. K., Mawlood-Yunis, A.-R., & Chatterjee, P. (2023). Sentiment Analysis of Twitter Posts on Global Conflicts. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2312.03715
  30. Shevtsov, A., Antonakaki, D., Lamprou, I., Kontogiorgakis, I., Pratikakis, P., & Ioannidis, S. (2023). Russo-Ukrainian War: Prediction and explanation of Twitter suspension. Proceedings of the International Conference on Advances in Social Networks Analysis and Mining, Pages 348 - 355348. https://doi.org/10.1145/3625007.3627317
  31. Syahputra, R., Yanris, G., & Irmayani, D. (2022). SVM and Naïve Bayes Algorithm Comparison for User Sentiment Analysis on Twitter. Sinkron, 7(2), 671-678. https://doi.org/10.33395/sinkron.v7i2.11430
  32. Thanh, P., Cho, M., Chang, C., & Chen, M. (2022). Short-Term Three-Phase Load Prediction With Advanced Metering Infrastructure Data in Smart Solar Microgrid Based Convolution Neural Network Bidirectional Gated Recurrent Unit. Ieee Access, 10, 68686-68699. https://doi.org/10.1109/access.2022.3185747
  33. Tsai, M. and Wang, Y. (2021). Analyzing Twitter Data to Evaluate People’s Attitudes towards Public Health Policies and Events in the Era of COVID-19. International Journal of Environmental Research and Public Health, 18(12), 6272. https://doi.org/10.3390/ijerph18126272
  34. Tufekci, Z. (2017). Twitter and tear gas: The power and fragility of networked protest. Yale University Press. https://doi.org/10.12987/9780300228175
  35. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Å., & Polosukhin, I. (2017). Attention Is All You Need. arXiv (Cornell University). https://doi.org/10.48550/arXiv.1706.03762
  36. Yadav, A., & Vishwakarma, D. K. (2020). A Deep Language-independent Network to analyze the impact of COVID-19 on the World via Sentiment Analysis. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2011.10358
  37. Yasir, M., Afzal, S., Latif, K., Chaudhary, G., Malik, N., Shahzad, F., … & Song, O. (2020). An Efficient Deep Learning Based Model to Predict Interest Rate Using Twitter Sentiment. Sustainability, 12(4), 1660. https://doi.org/10.3390/su12041660
  38. Yu, Q., Zhao, H., & Wang, Z. (2019). Attention-based bidirectional gated recurrent unit neural networks for sentiment analysis. Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition, Pages 116 - 119. https://doi.org/10.1145/3357254.3357262
  39. Zancanaro, M., Mrosek, M., Stabile, G., Othmer, C., & Rozza, G. (2021). Hybrid neural network reduced order modelling for turbulent flows with geometric parameters. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2107.09591

Downloads

Download data is not yet available.