An efficient two-pass classifier system for patient opinion mining to analyze drugs satisfaction. (March 2020)

• Record Type: Journal Article
• Authors: Padmavathy, P.; Pakkir Mohideen, S.
• Is Part Of: Biomedical signal processing and control. Volume 57(2020)
• Publication Date: 2020-03
• Subjects: Two-pass classifier -- Support vector machine -- Artificial neural network -- Opinion mining -- Customer reviews -- Drug satisfaction; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.101755
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Opinion mining is a well-known problem in natural language processing that increasing attention in recent years. With the rapid growth in e-commerce, reviews for popular products on the web have grown rapidly. The Two-pass classifier SVMNN is proposed to predict the given customer review is positive or negative. The performance of the proposed approach is analyzed using precision, recall, and F-measures. The experimentation results show that the proposed system attains the better result associated with the available methods. Abstract: Opinion mining is a well-known problem in natural language processing that increasing attention in recent years. With the rapid growth in e-commerce, reviews for popular products on the web have grown rapidly. In opinion mining, the greater part of the scientists has dealt with general domains, for example, electronic items, movies, and restaurants audit not much on health and medical domains. Therefore, in this paper, we focus on predicting the drug satisfaction level among the other patient who already experienced the effect of a drug using a novel Two-pass classifier. The Two-pass classifier is a combination of Support Vector Machine and Artificial Neural Network (SVMNN). Here, at first, we collect customer reviews from healthcare domain. After that, we extract the important features from each review and based on the features we generate the feature vector. Then, we apply two-pass classifier in order to predict the given customer review is positive or negative. The performance of the proposed approach is analyzed using precision, recall, and F-measures. The experimentation results show that the proposed system attains the better result associated with the available methods.