A Framework for Optimizing Ensemble Learning for Offensive Tweet Identification

Abstract

Online derogatory comments are ubiquitous on social media and areraising serious concerns across the globe. Social media data is riddenwith high dimensional search space due to noise, redundant features,and non-standardized writing style. These problems lead to high computationalcosts, longer training time, and low predictive accuracy inmachine learning models. The researchers proposed a framework for optimizingstacked generalized ensemble learning to address these problemsand enhance model performance. The main components of the frameworkinclude feature optimizer (FO), ensemble classifiers, and stratifiedK-foldCV (skfCV) through stacked generalization ensemble architecture.The ensemble classifiers, FO, and skfCV components make our methodstable and computationally efficient with the best performance. Theproposed method was validated using three benchmark datasets. The proposed method outperformed the state-of-the-art results in all theevaluation metrics used in those three articles adopted for comparison.