Emotion Detection from Tweets Using Ensemble Models

The informality and lack of structure in social media messages make emotion detection difficult. Our study introduced a novel approach to Twitter data analysis using a Genetic Algorithm (GA). This strategy combines various information to comprehend better users’ emotions, including writing style, sentiment, and linguistic patterns. A fine-tuned ensemble classifier using GA was employed to enhance the detection accuracy. Using a Twitter dataset for training and testing, we discovered that our model outperformed more conventional machine learning techniques. We explored many models and combinations, such as RF + SVM + XGB, Decision Tree, Random Forest, XGBoost, and SVM. The Average Soft-Voting Classifier (RF + MLP + LGBM) is an ensemble technique we investigated; they demonstrated promise for even better outcomes, with the ability to achieve 98% accuracy. Our results demonstrate that ensemble approaches greatly enhance the precision of social media emotion identification.