Abstract
Aspect-level sentiment analysis enables the identification of sentiment polarity toward specific aspects, providing more detailed information from healthcare reviews. This study aims to compare the performance of LSTM, BiLSTM, CNN-BiLSTM, and BERT for aspect-level sentiment classification. The dataset comprised a hybrid corpus of 5,000 reviews, including 2,000 real healthcare reviews and 3,000 AI-assisted synthetic reviews, covering five aspects: service quality, medical staff, facilities, waiting time, and cleanliness. The dataset was divided into 80% training data and 20% testing data. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results showed that BERT achieved the highest performance, with 94.60% accuracy, 94.78% precision, 94.40% recall, and a 94.59% F1-score, followed by CNN-BiLSTM, BiLSTM, and LSTM. Medical staff achieved the highest aspect-level accuracy at 95.8%, whereas waiting time obtained the lowest at 92.7%. These findings indicate that BERT achieved the best classification performance among the four evaluated models under the experimental conditions of this study.
References
Ahamad, R., & Mishra, K. N. (2025). Exploring sentiment analysis in handwritten and E-text documents using advanced machine learning techniques: A novel approach. Journal of Big Data, 12(1), 11. https://doi.org/10.1186/s40537-025-01064-2
Ahmed, Z., & Wang, J. (2023). A fine-grained deep learning model using embedded-CNN with BiLSTM for exploiting product sentiments. Alexandria Engineering Journal, 65, 731–747. https://doi.org/10.1016/j.aej.2022.10.037
Alhadlaq, A., & Altheneyan, A. (2024). Distilroberta2gnn: A new hybrid deep learning approach for aspect-based sentiment analysis. PeerJ Computer Science, 10, e2267. https://doi.org/10.7717/peerj-cs.2267
Bordoloi, M., & Biswas, S. K. (2023). Sentiment analysis: A survey on design framework, applications and future scopes. Artificial Intelligence Review, 56(11), 12505–12560. https://doi.org/10.1007/s10462-023-10442-2
Braig, N., Benz, A., Voth, S., Breitenbach, J., & Buettner, R. (2023). Machine learning techniques for sentiment analysis of COVID-19-related Twitter data. IEEE Access, 11, 14778–14803. https://doi.org/10.1109/ACCESS.2023.3242234
Chen, X., Xie, H., Qin, S. J., Chai, Y., Tao, X., & Wang, F. L. (2024). Cognitive-inspired deep learning models for aspect-based sentiment analysis: A retrospective overview and bibliometric analysis. Cognitive Computation, 16(6), 3518–3556. https://doi.org/10.1007/s12559-024-10331-y
Chifu, A.-G., & Fournier, S. (2023). Sentiment difficulty in aspect-based sentiment analysis. Mathematics, 11(22), 4647. https://doi.org/10.3390/math11224647
Cui, J., Wang, Z., Ho, S.-B., & Cambria, E. (2023). Survey on sentiment analysis: Evolution of research methods and topics. Artificial Intelligence Review, 56(8), 8469–8510. https://doi.org/10.1007/s10462-022-10386-z
Elhassan, N., Varone, G., Ahmed, R., Gogate, M., Dashtipour, K., Almoamari, H., El-Affendi, M. A., Al-Tamimi, B. N., Albalwy, F., & Hussain, A. (2023). Arabic sentiment analysis based on word embeddings and deep learning. Computers, 12(6), 126. https://doi.org/10.3390/computers12060126
Gutiérrez Benítez, R., Segura Navarrete, A., Vidal-Castro, C., & Martínez-Araneda, C. (2024). Guide for the application of the data augmentation approach on sets of texts in Spanish for sentiment and emotion analysis. PLOS ONE, 19(9), e0310707. https://doi.org/10.1371/journal.pone.0310707
Hua, Y. C., Denny, P., Wicker, J., & Taskova, K. (2024). A systematic review of aspect-based sentiment analysis: Domains, methods, and trends. Artificial Intelligence Review, 57(11), 296. https://doi.org/10.1007/s10462-024-10906-z
Rehman, S. U., Blessing, O. O., & Ali, A. (2025). A comparative study of X data about the NHS using sentiment analysis. Big Data and Cognitive Computing, 9(10), 244. https://doi.org/10.3390/bdcc9100244
Roumeliotis, K. I., Tselikas, N. D., & Nasiopoulos, D. K. (2024). Leveraging large language models in tourism: A comparative study of the latest GPT Omni models and BERT NLP for customer review classification and sentiment analysis. Information, 15(12), 792. https://doi.org/10.3390/info15120792
Singh, U., Abhishek, K., & Azad, H. K. (2024). A survey of cutting-edge multimodal sentiment analysis. ACM Computing Surveys, 56(9), 1–38. https://doi.org/10.1145/3652149
Taye, M. M., Abulail, R., Al-Ifan, B., & Alsuhimat, F. (2025). Enhanced sentiment classification through ontology-based sentiment analysis with BERT. Journal of Internet Services and Information Security, 15(1), 236–256. https://doi.org/10.58346/JISIS.2025.I1.015
Vamsidhar, D., Desai, P., Shahade, A. K., Patil, S., & Deshmukh, P. V. (2025). Hierarchical cross-modal attention and dual audio pathways for enhanced multimodal sentiment analysis. Scientific Reports, 15(1), 25440. https://doi.org/10.1038/s41598-025-09000-3
Weng, Y., Chen, L., Wang, S., Ye, X., Liu, X., & Liu, Z. (2024). MIECF: Multi-faceted information extraction and cross-mixture fusion for multimodal aspect-based sentiment analysis. Heliyon, 10(12), e32967. https://doi.org/10.1016/j.heliyon.2024.e32967
Yang, Y. (2025). Sentiment analysis of consumer reviews on online shopping platforms using integrated deep learning models. ICT Express, 11(5), 881–887. https://doi.org/10.1016/j.icte.2025.06.017
Zaid, S., Alharbi, A. H., & Samra, H. (2025). Multi-aspect sentiment classification of Arabic tourism reviews using BERT and classical machine learning. Data, 10(11), 168. https://doi.org/10.3390/data10110168
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright (c) 2026 Eka Prima Ginting, Danny Mario Tua Panjaitan