Paper Contents
Abstract
Text emotion detection plays a vital role in various applications, including sentiment analysis, mental health monitoring, customer feedback systems, and human-computer interaction. The complexity of natural language, including context dependency, sarcasm, and implicit emotions, poses significant challenges in accurately identifying emotions from textual data. This research explores an advanced hybrid approach that integrates Convolutional Neural Networks, Recurrent Neural Networks, and Transformer models to enhance emotion classification accuracy. The model effectively captures semantic meaning, sentence structure, and emotional intensity from text by combining local feature extraction, sequential pattern recognition, and contextual understanding capabilities. Evaluated on standard benchmark datasets, the approach demonstrates improved performance in detecting emotions such as joy, sadness, anger, surprise, fear, and disgust with 92.80% validation accuracy.
Copyright
Copyright © 2025 Deepsikasri R G. This is an open access article distributed under the Creative Commons Attribution License.
