Optimizing Feature Selection in Spam Email Detection Using Co-Evolutionary Algorithms

The Co-Evolutionary Algorithms for Feature Selections delve into feature selection in the context of data-rich environments. The study aims to identify and implement a suitable co-evolutionary feature selection method for the classification of spam emails. By exploring co-evolutionary algorithms and their application in solving feature selection challenges, the research investigates the transformation of feature selection issues into optimization problems. Through the utilization of co-evolutionary algorithms, the study analyzes and compares the outcomes with other established feature selection methods in machine learning. The findings highlight the effectiveness of co-evolutionary algorithms in feature selection, particularly in the classification of spam emails, showcasing their potential for broader applications in text classification tasks. The thesis contributes to the understanding of feature selection methodologies and their practical implications in enhancing classification accuracy and efficiency in data processing tasks.