Comparative Analysis of Emotion Detection Techniques Using Machine Learning

Abstract

Emotion detection has emerged as a keyfocus area of research in human-computer interactiondomain that allows systems to more effectively reactto human emotional states. This paper presents a comparative analysis of various emotion detection techniques using machine learning. We evaluate and compare the performance of different machine learning classifiers, including Bagging, K-Nearest Neighbor(KNN), and Random Forests. The study involves the use of several publicly available datasets. The paper explores the benefits and constraints of each technique with respect to accuracy and computational efficiency, offering a comprehensive overview of current approaches in the field. The findings suggest that while Random Forest algorithm outperforms KNN and Bagging techniques regarding accuracy. This work contributes valuable insights into selecting the most suitable emotion detection technique for different application scenarios.A comparative analysis of the classification algorithms is provided with the three considered datasets by computing the accuracy with recall, precision, and F-measure metrics. In the experimental results, RF algorithm archives a higher accuracy of 86%, 96%, and85% in Dataset1, Dataset2, and Dataset3 respectively which is better than the others considered algorithms.