Related Experiment Video
Updated: Jan 13, 2026
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
5.3K
A novel hybrid attention based deep learning framework for textual emotion recognition using natural language
Mohammed Abdullah Al-Hagery1, Abeer A K Alharbi2, Abdulwhab Alkharashi3
1Department of Computer Science, College of Computer, Qassim University, Buraydah, Saudi Arabia. hajry@qu.edu.sa.
Scientific Reports
|October 29, 2025
Summary
This study introduces a novel deep learning technique for recognizing emotions in text, enhancing assistive technologies for individuals with disabilities. The method achieved 98.86% accuracy, improving understanding and support for disabled persons.
Area of Science:
- Artificial Intelligence
- Natural Language Processing
- Computational Linguistics
Background:
- Disability presents significant challenges, often limiting individual involvement and growth.
- Assistive technologies are crucial for enhancing the independence and quality of life for people with disabilities.
- Emotion detection from text is vital for developing more responsive and empathetic technological solutions.
Purpose of the Study:
- To propose a Novel Hybrid Attention-Based Deep Learning for Textual Emotion Recognition Using Natural Language Processing Technologies (HADLTER-NLPT).
- To improve assistive technologies and emotional understanding for disabled persons through accurate text-based emotion recognition.
- To enhance the capabilities of machine learning in creating supportive environments for individuals with disabilities.
Main Methods:
- Text pre-processing for data cleaning and normalization.
- Word2Vec for semantic word embedding.
- Hybrid Attention-based Long Short-Term Memory (HA-LSTM) for emotion classification.
- Oscillating Chaotic Sunflower Optimization (OCSFO) for hyperparameter tuning.
Main Results:
- The HADLTER-NLPT technique demonstrated superior performance in textual emotion recognition.
- Achieved a high accuracy of 98.86% on the Emotion detection from text dataset.
- Outperformed existing models in recognizing emotional expressions from textual data.
Conclusions:
- The HADLTER-NLPT model offers a significant advancement in emotion detection from text.
- This technology can substantially benefit the development of assistive tools for disabled individuals.
- The proposed method highlights the potential of deep learning and NLP in addressing challenges faced by people with disabilities.
