AI-driven educational transformation in ICT: Improving adaptability, sentiment, and academic performance with...

Area of Science:

• Educational Technology
• Artificial Intelligence in Education
• Data Science in Education

Background:

• The integration of advanced computational methods is crucial for addressing complex challenges in modern education.
• Understanding student adaptability and sentiment is key to personalizing learning experiences and improving outcomes.

Purpose of the Study:

• To deploy state-of-the-art machine learning (ML) and deep learning (DL) strategies for educational improvement.
• To analyze student adaptability, sentiment, and academic performance using a robust dataset.
• To explore the implications of AI in enhancing teacher effectiveness, educational leadership, and student well-being.

Main Methods:

• A hybrid stacking approach combining Decision Trees, Random Forest, and XGBoost as base learners with Gradient Boosting as a meta-learner.
• Convolutional Neural Network (CNN) for sentiment analysis.
• Recurrent Convolutional Neural Network (RCNN), Random Forests, and Decision Trees for analyzing educational data complexity.
• Bagging XGBoost algorithm for model aggregation.

Main Results:

• The hybrid stacking model achieved 90% accuracy in predictions.
• The CNN model demonstrated 89% accuracy in sentiment analysis.
• The bagging XGBoost algorithm reached 88% accuracy, highlighting its utility in enhancing academic performance.
• Analysis revealed complex interrelationships within ML models and educational contexts.

Conclusions:

• The study demonstrates the significant potential of ML and DL in improving educational technology and practices.
• AI-driven insights can inform instructional strategies, leading to enhanced teaching effectiveness and student engagement.
• The findings support data-driven decision-making for educational leadership, promoting academic success and a positive learning environment.
• This research aligns with sustainable ICT in education objectives, paving the way for future AI innovations.