Drug Recommendation System Based on Sentiment Analysis of Drug Reviews Using Machine Learning

Rishitha Bontha, Sabreen Taj Bandar, Siddu Veera Venkatesh Barigela, Susmitha Gangappagari, Nalini Priyanka Kummara

2025

Abstract

People Self-Medicate Without Physicians Advice, Making Their Conditions Worse in Some Cases While The COVID-19 Pandemic Has Further Exposed Inadequacies in The System. To address this, this study develops a machine learning-based drug recommendation system that uses sentiment analysis of patient reviews to recommend drugs. The system uses vectorization methods Bag of Words (Bo W), TFIDF, Word2Vec to convert textual drugs reviews into organized sentiment information. Classification models such as MLP then evaluate sentiments and create drug recommendations. Results evaluated by precision, recall, F1-score, accuracy, and AUC scores confirm that MLP classifier model out performs the rest of models in accuracy. This model offers an inherent advantage over current systems that rely on patient demographics and risk groups, greatly alleviating cold start issues, computational resource consumption, and information sparsity. It comprises a set of classifiers and uses a useful count, that is, a number that measures the number of times a particular drug has been reviewed to ensure that only the most reliable drugs are recommended to each patient. The hybrid approach featured in our model improves predictive robustness, outperforming traditional methods by yielding superior performance and reliability. Notably, it also fosters computational efficiency by choosing the fastest algorithms, resulting in greatly minimized training times and enhanced prediction accuracies. This novel framework provides a scalable, data driven method for generating automated pharmaceutical suggestions.

Paper Citation

in Harvard Style

Bontha R., Bandar S., Barigela S., Gangappagari S. and Kummara N. (2025). Drug Recommendation System Based on Sentiment Analysis of Drug Reviews Using Machine Learning. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 516-523. DOI: 10.5220/0013901000004919

in Bibtex Style

@conference{icrdicct`2525,
author={Rishitha Bontha and Sabreen Bandar and Siddu Barigela and Susmitha Gangappagari and Nalini Kummara},
title={Drug Recommendation System Based on Sentiment Analysis of Drug Reviews Using Machine Learning},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={516-523},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013901000004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Drug Recommendation System Based on Sentiment Analysis of Drug Reviews Using Machine Learning
SN - 978-989-758-777-1
AU - Bontha R.
AU - Bandar S.
AU - Barigela S.
AU - Gangappagari S.
AU - Kummara N.
PY - 2025
SP - 516
EP - 523
DO - 10.5220/0013901000004919
PB - SciTePress