Find in Library

This research aims to develop a fast and adaptive sentiment evaluation approach related to the use of white paracetamol using a combination of the K-Nearest Neighbors (KNN) algorithm, Synthetic Minority Over-Sampling Technique (SMOTE), and the Receptive Deciding concept. Imbalances in the dataset, where positive sentiment may predominate, are addressed through the use of SMOTE to synthesize minority class samples. The KNN algorithm is applied to build a sentiment classification model, while Receptive Deciding is used to provide adaptive intelligence to changes in sentiment. The SMOTE oversampling process is carried out to achieve class balance, while KNN is used to classify sentiment. Receptive Deciding is applied to increase the model's adaptability to changes in sentiment. The research results show that the integration of the SMOTE, KNN, and Receptive Deciding methods provides an effective approach in assessing sentiment accurately and adaptively. The developed model is able to recognize changes in sentiment over time and provide balanced evaluation results. These findings are expected to contribute to understanding public sentiment towards the use of white paracetamol, as well as being the basis for developing more effective health communication strategies.