TRANSFORMER-BASED SENTIMENT ANALYSIS FOR PUBLIC OPINION CLASSIFICATION ON ELECTRIC VEHICLE ADOPTION USING NATURAL LANGUAGE PROCESSING
DOI:
https://doi.org/10.61677/jth.v4i1.840Keywords:
Transformer, Natural Language Processing, sentiment analysis, Electric Vehicle Adoption, public opinionAbstract
The growth of electric vehicle (EV) adoption has generated extensive public discussions on digital platforms, reflecting diverse perceptions of environmental benefits, economic feasibility, technological readiness, and government policies. This study aims to develop a Transformer-based Natural Language Processing (NLP) framework for classifying public sentiment toward EV adoption using textual data from social media and digital platforms. A quantitative experimental approach was applied through data collection, preprocessing, sentiment and emotion labeling, Transformer-based modeling, and performance evaluation. The dataset consisted of 5,000 public opinion texts, of which 3,785 records were retained after data cleaning and selection. Sentiment classification included three categories: positive, negative, and neutral, while emotion classification consisted of happy, trust, angry, fear, disappointed, and surprise. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results showed that positive sentiment was dominant, accounting for 43.46% of the analyzed opinions, followed by negative sentiment at 31.97% and neutral sentiment at 24.57%. Positive opinions were mainly related to environmental benefits and energy efficiency, whereas negative opinions reflected concerns about vehicle prices, charging infrastructure, charging time, and battery replacement costs. These findings indicate that Transformer-based NLP can capture contextual semantic information from large-scale public opinion data and support reliable sentiment classification. The proposed framework provides practical value for policymakers, researchers, and industry stakeholders in developing data-driven strategies to promote EV adoption and sustainable transportation.
References
Abbassy, M. M., Ead, W. M., El-Shora, A. I. A., & Aboalndr, A. M. (2026). Uncovering advanced transfer learning strategies for deep neural networks in natural language processing. Scientific Reports, 16(1), 1–10. https://doi.org/10.1038/s41598-026-39819-3
Ashari, N., Mifta Al Firdaus, M. Z., Budi, I., Santoso, A. B., & Kresna Putra, P. (2023). Analyzing public opinion on electrical vehicles in Indonesia using sentiment analysis and topic modeling. ICCoSITE 2023 - International Conference on Computer Science, Information Technology and Engineering, 461–465. https://doi.org/10.1109/ICCOSITE57641.2023.10127834
Ashayeri, M., & Abbasabadi, N. (2024). Unraveling energy justice in NYC urban buildings through social media sentiment analysis and transformer deep learning. Energy and Buildings, 306, 113914. https://doi.org/10.1016/j.enbuild.2024.113914
Audyna, A. P., Sholikah, R. W., Ginardi, R. V. H., & Hernandez, R. M. (2024). Aspect-based sentiment analysis on social media X for electric vehicles (EV) in Indonesia using IndoBERT and machine learning. 2024 9th International Conference on Informatics and Computing (ICIC 2024). https://doi.org/10.1109/ICIC64337.2024.10956679
Balla, S. N., Pani, A., Sahu, P. K., & González-Feliu, J. (2023). Examining shifts in public discourse on electric mobility adoption through Twitter data. Transportation Research Part D: Transport and Environment, 121, 103843. https://doi.org/10.1016/j.trd.2023.103843
Bau, R. T. R. L., Hermila, A., & Latief, M. (2024). Electric vehicle adoption in Indonesia: Insights from sentiment analysis of major news portals. 2024 International Conference on Data Science and Its Applications (ICoDSA 2024), 475–480. https://doi.org/10.1109/ICODSA62899.2024.10651692
Cong, C., Song, Y., Di Ieva, A., Jin, Q., Fan, L., Chou, A., J Gill, A., & Liu, S. (2026). Slide-aware deep feature prompting for enhanced whole slide image classification. Expert Systems with Applications, 331(PA), 133079. https://doi.org/10.1016/j.eswa.2026.133079
Daniati, E., Nugroho, A., Ristyawan, A., & Utama, H. (2026). Perbandingan kinerja algoritma SVM, LSTM, dan fine-tuned IndoBERT dalam analisis sentimen opini masyarakat Indonesia terhadap mobil listrik. The Indonesian Journal of Computer Science Research, 5(1), 1–13. https://doi.org/10.59095/IJCSR.V5I1.245
del Rey, S., Cruz, L., Franch, X., & Martínez-Fernández, S. (2027). Estimating Deep Learning energy consumption based on model architecture and training environment. Computer Standards and Interfaces, 99(May 2026), 104170. https://doi.org/10.1016/j.csi.2026.104170
Dewi, B. E. S. (2025). Sentiment analysis model on electric vehicles using IndoBERTweet and IndoBERT algorithm. Antivirus: Jurnal Ilmiah Teknik Informatika, 19(2), 192–202. https://doi.org/10.35457/W5R3G517
Ha, S., Marchetto, D. J., Dharur, S., & Asensio, O. I. (2021). Topic classification of electric vehicle consumer experiences with transformer-based deep learning. Patterns, 2(2), 100195. https://doi.org/10.1016/j.patter.2020.100195
H.M., F. A. J., & Hardiansyah, B. (2026). Analisis sentimen terhadap ulasan online untuk kendaraan listrik menggunakan deep learning di Platform X. JATI (Jurnal Mahasiswa Teknik Informatika), 10(1), 1458–1465. https://doi.org/10.36040/JATI.V10I1.17094
Hu, X., Gu, H., & Tang, Y. (2027). An embedding-based approach for measuring science–technology topic linkages using LLMs. Information Processing and Management, 64(1), 104983. https://doi.org/10.1016/j.ipm.2026.104983
Jabbar, A., Yuan, J., Al-Shamasneh, A. R., & Rekik, S. (2026). BERT based sentiment analysis of consumer hesitancy toward solar energy adoption. Scientific Reports, 16(1), 8397. https://doi.org/10.1038/s41598-026-38604-6
Kastrati, Z., Imran, A. S., Daudpota, S. M., Memon, M. A., & Kastrati, M. (2023). Soaring energy prices: Understanding public engagement on Twitter using sentiment analysis and topic modeling with transformers. IEEE Access, 11, 26541–26553. https://doi.org/10.1109/ACCESS.2023.3257283
Kumar, S., & Gawade, S. (2023). Sentiment analysis of opinions about electric vehicles using Twitter data. 2023 IEEE 7th Conference on Information and Communication Technology (CICT 2023). https://doi.org/10.1109/CICT59886.2023.10455654
Li, Y., Tang, J. H. C. G., Wang, S., Peng, Z., & Zhuge, C. (2025). Attention and attitudes of Chinese social media users towards autonomous vehicles: Sentimental, statistical and spatiotemporal perspectives. Transportation, 1–31. https://doi.org/10.1007/s11116-025-10644-3
Mnassri, K., Farahbakhsh, R., & Crespi, N. (2027). MultiSent-RAG: A retrieval and memory-augmented system for multilingual sentiment processing. Information Processing and Management, 64(1), 104990. https://doi.org/10.1016/j.ipm.2026.104990
Myneni, M. B., Akkineni, H., Mai, C. K., & Boppana, S. (2024). Analytical framework to understand electric vehicle adoption by leveraging sentiment analysis. Journal of Mobile Multimedia, 20(5), 1067–1088. https://doi.org/10.13052/JMM1550-4646.2054
Sathyan, S., Peedikayil, J. J., Ravikumar Pandi, V., & Salkuti, S. R. (2023). Two-layered machine learning approach for sentiment analysis of tweets related to electric vehicles. Proceedings - 2023 International Conference on Innovations in Engineering and Technology (ICIET 2023). https://doi.org/10.1109/ICIET57285.2023.10220717
Shi, L., Ou, S., Zhou, Y., Wu, Y., Tan, X., He, X., De Castro Gomez, D. J., & Lin, Z. (2025). Assessing Chinese user satisfaction with electric vehicle battery performance from online reviews. Transportation Research Part D: Transport and Environment, 141, 104644. https://doi.org/10.1016/j.trd.2025.104644
Wang, S., Kulkarni, K., & Deb, S. (2025). Evaluating sentiment analysis models for enhancing electric vehicle charging infrastructure planning. 2025 IEEE/AIAA Transportation Electrification Conference and Electric Aircraft Technologies Symposium (ITEC+EATS 2025). https://doi.org/10.1109/ITEC63604.2025.11098052
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 JTH: Journal of Technology and Health
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
