Multi-Layer Perception for Drug Recommendation System based on Sentiment Analysis of Drug Reviews

Abstract

Since coronavirus has shown up, inaccessibility of legitimate clinical resources is at its peak, like the shortage of specialists and healthcare workers, lack of proper equipment and medicines etc. The entire medical fraternity is in distress, which results in numerous individual's demise. Due to unavailability, individuals started taking medication independently without appropriate consultation, making the health condition worse than usual. As of late, machine learning has been valuable in numerous applications, and there is an increase in innovative work for automation. This work intends to present a drug recommender system that can drastically reduce specialist’s heap. To overcome from above problem author of this paper introducing sentiment and machine learning based drug recommendation system which will accept disease names from patient and then recommend DRUG and simultaneously display SENTIMENT rating based on reviews given by old users based on their experience. If predicted rating is high then patient can trust and took recommended drug. The proposed work has used various features extraction algorithms such as TF-IDF (term frequency –
inverse document frequency), BAG of WORDS and WORVEC and these extracted features will be applied on various machine learning algorithm such as Logistic Regression, Linear SVC, Ridge classifier, Naïve Bayes, Multilayer Perceptron classifier (MLP), SGD classifier and many more. The MLP classifier with TF-IDF feature extraction will resulted in superior performance compared to other models. To implement this work, DRUGREVIEW dataset was used from UCI machine learning website