Since the coronavirus emerged, it has been increasingly difficult to get legitimate therapeutic resources, such as the scarcity of specialists and healthcare professionals, appropriate equipment and medications, etc. There are many deaths as a result of the medical profession as a whole being in turmoil. Due to a lack of availability, people began taking medication on their own without the proper consultation, which made their health situation worse than usual. Recently, machine learning has proven useful in a variety of applications, and creative work automation is on the rise. This research article aims to propose a system for prescribing medications that can significantly reduce the workload of specialists. In this research project, we develop a drug recommendation system that makes use of patient reviews to forecast sentiment using a variety of vectorization techniques, including Bow, TF-IDF, Word2Vec, and manual feature analysis, which can support the recommendation of the best medication for a given disease by various classification algorithms. Precision, recall, f1score, accuracy, and AUC score were used to assess the anticipated sentiments. The Sequential Model and XGBoost classifier surpass all other models with roughly 95% accuracy, according to the data. We implemented this model in a real-world setting in which users can log in, submit their symptoms, and receive a list of medicines that are recommended for their condition