The integration of Human-AI collaboration in education has emerged
as a transformative approach to personalize learning experiences and
address diverse student needs. Traditional learning systems often fail
to adapt to individual learning styles and preferences, creating
challenges in maintaining engagement and improving outcomes. Deep
learning and natural language processing (NLP) techniques offer
innovative solutions to these challenges by analyzing learner behavior,
understanding natural language inputs, and generating adaptive
recommendations. This study proposes a novel framework for
personalized learning systems that leverages deep learning models,
such as Transformer-based architectures, and advanced NLP
techniques to dynamically analyze student inputs, progress, and
preferences. The framework includes human oversight to ensure
ethical and pedagogically sound interventions. Using a dataset of
10,000 anonymized student interactions, the proposed system predicts
learning trajectories with an accuracy of 92.5% and generates
personalized recommendations with 89% relevance, significantly
improving upon traditional recommendation systems by 14%. Results
demonstrate the system’s ability to enhance student engagement, with
a 20% increase in time-on-task and a 25% improvement in content
retention scores compared to non-adaptive systems. Additionally,
teacher feedback highlights a 30% reduction in workload due to
automated grading and content suggestion features. The findings
underline the potential of Human-AI collaboration to foster an
inclusive, efficient, and engaging learning environment.
S. Sebastin Antony Joe
Gulf College, Sultanate of Oman
Personalized Learning, Deep Learning, Natural Language Processing, Human-AI Collaboration, Adaptive Education Systems
| January | February | March | April | May | June | July | August | September | October | November | December |
| 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 15 , Issue: 4 , Pages: 3695 - 3703 )
Date of Publication :
January 2025
Page Views :
15
Full Text Views :
2
|