Sentiment classification of user's reviews on drugs based on global vectors for word representation and bidirectional long short-term memory recurrent neural network

Abstract

The process of product development in the health sector, especially pharmaceuticals, goes through a series of precise procedures due to its direct relevance to human life. The opinion of patients on a particular drug can be relied upon in this development process, as the patients convey their experience with the drugs through their opinion. The social media field provides many datasets related to drugs through knowing the user's rating and opinion on a drug after using it. In this work, a dataset is used that includes the user's rating and review on the drug, for the purpose of classifying the user's opinions (reviews) whether they are positive or negative. The proposed method includes two phases. The first phase is to use the global vectors for word representation model for converting texts into the vector of embedded words. As for the second stage, the deep neural network (bidirectional long short-term memory) is employed in the classification of reviews. The user's rating is used as a ground truth in evaluating the classification results. The proposed method presents encouraging results, as the classification results are evaluated through three criteria, namely precision, recall and F-score, whose obtained values equal (0.9543, 0.9597 and 0.9558), respectively.