Abstract-Based Sentiment Analysis with Drug Recommendation System
DOI:
https://doi.org/10.63503/acset.138Keywords:
Sentiment Analysis, Bidirectional Long Short-Term Memory (BiLSTM), Drug Recommendation System, Deep Learning, Natural Language Processing, Healthcare Text MiningAbstract
The rapid growth of the internet has enabled a geometric increase in user-generated healthcare content, with patients often writing reviews of their experiences with the drugs they are taking. Such reviews are extremely important for understanding how drugs work in the body. Thus, a framework is proposed to develop a system for recommending drugs based on medical condition classifications using Sentiment Analysis. The system is based on Natural Language Processing techniques such as data cleaning, tokenisation, and lemmatisation to convert unstructured reviews to machine-understandable structures. Various system architectures are proposed, including traditional machine learning-based structures and deep learning-based structures such as CNN, LSTM, and BERT. Utilising different datasets made available via various online sources, such as Drugs.com, experimental results establish the efficacy of the suggested framework, with an accuracy of 94.4% for condition classification using the Passive Aggressive Classifier, and 94.85% for sentiment prediction using Logistic Regression. The proposed engine filters out the highest-rated drugs based on patient-validated "useful counts" and sentiment analysis. This study suggests an effective tool for public health surveillance through sentiment analysis, aiding individuals in choosing from extensive medical treatments.
References
[1] L. L. a. S. V. B. Pang, “Thumbs up? Sentiment classification using machine learning techniques,” in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), 2002.
[2] S. Al-Hadhrami, “Deep learning-based method for sentiment analysis of patients’ drug reviews,” 2024.
[3] A. Nikfarjam, A. Sarker, K. O’Connor, R. Ginn, and G. Gonzalez, “Pharmacovigilance from social media: Mining adverse drug reactions,” J. Biomed. Informatics, vol. 54, pp. 202–212, 2015.
[4] C. C. Rodríguez and I. Segura-Bedmar, “Comparing deep learning architectures for sentiment analysis on drug reviews,” J. Biomed. Informatics, vol. 110, 2020.
[5] W. Liu et al., “Characterizing public sentiments and drug interactions using social media,” J. Med. Internet Res., 2025.
[6] N. R. Wijenayake and U. Wijenayake, “Drug recommendation system based on medical condition classification and sentiment analysis,” 2025.
[7] B. Liu, Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge, U.K.: Cambridge Univ. Press, 2015.
[8] R. Feldman, “Techniques and applications for sentiment analysis,” Communications of the ACM, vol. 56, no. 4, pp. 82–89, 2013.
[9] K. D. et al., “Sentiment analysis in healthcare: State of the art,” Artificial Intelligence in Medicine, vol. 98, pp. 1–14, 2019.
[10] P. D. Turney, “Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews,” in Proc. 40th Annu. Meeting Assoc. Comput.Linguistics (ACL), 2002, pp. 417–424.
[11] T. M. Na and H. K. J. Kim, “Rule-based sentiment classification of drug reviews,” J. Biomed. Informatics, vol. 45, no. 4, pp. 789–798, 2012.
[12] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[13] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673–2681, 1997.
[14] C. C. Rodríguez and I. Segura-Bedmar, “Comparing deep learning architectures for sentiment analysis on drug reviews,” J. Biomed. Informatics, vol. 110, 2020.
[15] Y. Zhang and G. F. M. Zhang, “Hybrid CNN–BiLSTM based sentiment classification,” Knowledge-Based Systems, vol. 228, 2021.
[16] L. Zhang et al., “Deep learning for aspect-based sentiment analysis: A review,” PeerJ Computer Science, vol. 8, 2022.
[17] N. R. Wijenayake and U. Wijenayake, “Drug recommendation system based on medical condition classification and sentiment analysis,” 2025.
[18] D. Wang and J. Zhang, “Medical recommender systems: A survey,” Journal of Biomedical Informatics, vol. 95, 2019.
[19] F. Ricci, L. Rokach, and B. Shapira, Recommender Systems Handbook, 2nd ed. New York, NY, USA: Springer, 2015.
[20] J. Bobadilla, F. Ortega, A. Hernando, and A. Gutiérrez, “Recommender systems survey,” Knowledge-Based Systems, vol. 46, pp. 109–132, 2013.
[21] S. Garg, “Drug recommendation system using machine learning,” 2021.
[22] T. Mikolov et al., “Efficient estimation of word representations in vector space,” in Proc. ICLR, 2013.
[23] J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” in Proc. EMNLP, 2014, pp. 1532–1543.
[24] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.
[25] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[26] A. Mishra and A. A. A. Mishra, “Mining patient drug reviews for adverse drug reactions,” in Proc. IEEE Int. Conf. Bioinformatics and Biomedicine (BIBM), 2015, pp. 1416–1421.
[27] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[28] G. Shani and A. Gunawardana, “Evaluating recommendation systems,” in Recommender Systems Handbook, F. Ricci et al., Eds. New York, NY, USA: Springer, 2015, pp. 265–308.
[29] A. Sarker, K. O’Connor, R. Ginn, K. Scotch, K. Smith, Y. Malone, and G. Gonzalez, “Social media mining for toxicovigilance: Automatic monitoring of prescription medication abuse from Twitter,” Journal of Biomedical Informatics, vol. 54, pp. 202–212, 2016.
[30] F. Greaves, D. Ramirez-Cano, C. Millett, A. Darzi, and L. Donaldson, “Harnessing the cloud of patient experience: Using social media to detect poor quality healthcare,” BMJ Quality & Safety, vol. 22, no. 3, pp. 251–255, 2013.
[31] S. Gao, J. He, and X. Chen, “Deep learning for sentiment analysis in medical text,” IEEE Access, vol. 7, pp. 123456–123465, 2019.
[32] F. Gräßer, S. Kallumadi, V. Malberg, and S. Zaunseder, “Aspect-based sentiment analysis of drug reviews applying cross-domain and cross-data learning,” in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), 2018, pp. 1–10.
[33] Y. Zhang, Q. Chen, Z. Yang, H. Lin, and Z. Lu, “BioWordVec: Improving biomedical word embeddings with subword information and MeSH,” Scientific Data, vol. 6, no. 1, pp. 1–9, 2019.
[34] E. Tutubalina, S. Malykh, V. Nikolenko, and A. Loukachevitch, “Drug review mining: Sentiment analysis and drug effectiveness detection,” Journal of Biomedical Informatics, vol. 119, 2021.
[35] J. Lee, W. Yoon, S. Kim, D. Kim, S. Kim, C. H. So, and J. Kang, “BioBERT: A pre-trained biomedical language representation model for biomedical text mining,” Bioinformatics, vol. 36, no. 4, pp. 1234–1240,2020.
[36] I. Beltagy, K. Lo, and A. Cohan, “SciBERT: A pretrained language model for scientific text,” in Proc. Cnf. Empirical Methods in Natural Language Processing (EMNLP), 2019, pp. 3615–3620.
[37] Y. Gu, R. Tinn, H. Cheng, M. Lucas, N. Usuyama, X. Liu, T. Naumann, J. Gao, and H. Poon, “Domain-specific language model pretraining for biomedical natural language processing,” ACM Transactions on Computing for Healthcare, vol. 3, no. 1, pp. 1–23, 2021.
[38] Y. Zhang and X. Chen, “Explainable recommendation: A survey and new perspectives,” Foundations and Trends in Information Retrieval, vol.14, no. 1, pp. 1–101, 2020.
[39] M. Jiang, Y. Jiang, and H. Zhi, “Artificial intelligence in healthcare: Past, present and future,” Stroke and Vascular Neurology, vol. 2, no. 4, pp. 230–243, 2017.
[40] T. Tran, T. D. Nguyen, D. Phung, and S. Venkatesh, “Learning to recommend drugs using deep learning,” in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), 2018, pp. 2458–2466.
[41] A. Mustaqeem and S. Anwar, “Sentiment analysis of drug reviews using machine learning techniques,” IEEE Access, vol. 9, pp. 156870–156880, 2021.
[42] O. Alqaryouti, N. Siyam, and M. Alkhatib, “Patient feedback analysis for drug recommendation using natural language processing,” Healthcare Informatics Research, vol. 28, no. 2, pp. 150–160, 2022.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Adroid Conference Series: Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
