EmoBlend Fusion: Leveraging Handcrafted and Deep Features for Emotion Detection

Correct detection of human emotions plays a vital role in human-machine communication and decision-making. Recent advancements in large language models (LLMs) have sparked research in opinion mining, emotion detection, and sentiment analysis. While features extracted from texts using pre-trained LLMs can capture patterns effectively, integrating domain-specific handcrafted features remains crucial for constructing predictive models using user-generated microblogs. This paper proposes EmoBlend Fusion, a hybrid emotion detection model incorporating handcrafted features and latent deep features using pre-trained embeddings extracted from tweets. While the handcrafted features are trained using an ensemble of random forest, XGBoost, and linear SVM classifiers, a new bidirectional convolutional neural network-based model is trained using the deep features. Model predictions are then fused through a weighted ensemble mechanism for classifying emotions into one of the six distinct classes: sadness, joy, love, anger, fear, and surprise. The experimental results demonstrate that the proposed model outperforms the state-of-the-art techniques, achieving the highest recall (0.94), precision (0.95), accuracy (0.94), and F1-score (0.94) on a benchmark Twitter emotion detection dataset.