What question did this study set out to answer?

The aim is to classify user-written drug reviews regarding pain, depression, and birth control using various machine learning techniques.

April 4, 2026

A comparative approach on classification of medical condition drug reviews using multiple traditional and neural network-based models

Key Points

The aim is to classify user-written drug reviews regarding pain, depression, and birth control using various machine learning techniques.
Applied natural language processing techniques for sentiment analysis.
Employed six machine learning models including neural networks and traditional approaches.
Utilized tokenization with TF-IDF for traditional models and word embeddings for neural networks.
Evaluated models using precision, accuracy, recall, and F1-score metrics.
Convolutional neural networks achieved the highest F1-score of 0.991.
Simple neural networks followed closely with an F1-score of 0.985.
Random Forest also performed well with an F1-score of 0.980.

Abstract

This paper uses national language processing techniques to perform sentiment analysis, classifying user-written drug reviews for pain, depression, and birth control. Six machine learning (ML)-based models are employed for analysis, including neural networks (NNs) like the simple NN and convolutional neural networks (CNNs), as well as more conventional models like Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT), and Support Vector Classification (SVC). Tokenization used TF-IDF for traditional models and word embeddings for CNN and a simple NN. Using precision, accuracy, recall, and F1-score, CNN achieved the highest F1-score (0.991), followed by NN (0.985) and RF (0.980).

Bookmark

A comparative approach on classification of medical condition drug reviews using multiple traditional and neural network-based models

Key Points

Abstract

Cite This Study