Human-Centered Artificial Intelligence in Education 2

Pushan Kumar Dutta is an associate professor in the Electronics and Communication Engineering Department at ASETK, Amity University, Kolkata, India.
Vasileios Paliktzoglou holds a PhD in Computer Science from the University of Eastern Finland.
Sonal Trivedi is an associate professor at the School of Business, Manav Rachna University, India.

Preface xi
Pushan KUMAR DUTTA and Sonal TRIVEDI
Part 1. AI Models, Prediction Systems and Analytics in Education 1
Chapter 1. Enhancing Student Performance Prediction Using Metaheuristic-optimized SAINT Deep Learning Models 3
Sayed ELKENAWY
1.1. Introduction 4
1.2. Literature review 6
1.3. Material and methods 8
1.3.1. Dataset description 8
1.3.2. Data preprocessing 11
1.3.3. Deep learning models 14
1.4. Empirical results 15
1.4.1. Baseline model results 15
1.5. Hyperparameter optimization results 18
1.6. Conclusion and future work 21
1.7. Acknowledgments 23
1.8. References 23
Chapter 2. Enhanced Student Exam Performance Prediction via Ninja-optimized Neural Ordinary Differential Equation (NODE) 27
S.K. TOWFEK and Ebrahim A. MATTAR
2.1. Introduction 27
2.1.1. Study contributions 29
2.2. Literature review 30
2.3. Materials and methods 34
2.3.1. Dataset description and preprocessing 34
2.3.2. Data preprocessing 37
2.3.3. DL models 38
2.4. Empirical results 40
2.4.1. Deep learning performance key takeaways 40
2.4.2. Hyperparameter optimization results 42
2.5. Conclusion and future work 46
2.6. Acknowledgments 47
2.7. References 48
Chapter 3. Intelligent College Placement Prediction Using a Hybrid FT-Transformer Framework Optimized by Metaheuristic Algorithms 51
Mahmoud Elshabrawy MOHAMED, Amal H. ALHARBI, Amel Ali ALHUSSAN and Shahid MAHMOOD
3.1. Introduction 51
3.2. Literature review 55
3.3. Materials and methods 58
3.3.1. Dataset description and preprocessing 58
3.3.2. Data preprocessing 61
3.4. DL models 63
3.4.1. FT-Transformer architecture description 63
3.4.2. Motivation for optimization 64
3.5. Empirical results 64
3.5.1. DL performance: key takeaways 64
3.6. Hyperparameter optimization results 68
3.7. Conclusion and future work 72
3.8. Acknowledgments 73
3.9. References 73
Chapter 4. An Intelligent DeepFM Framework Optimized by Metaheuristic Algorithms for Predicting Students' Adaptability in Online Learning 77
Khaled Sh. GABER, Doaa Sami KHAFAGA, Marwa M. EID and Asifa IQBAL
4.1. Introduction 78
4.2. Literature review 81
4.3. Materials and methods 87
4.3.1. Dataset description 87
4.3.2. Preprocessing description 89
4.4. Deep learning models 90
4.4.1. Motivation for optimization: substantial improvement with SSO 92
4.5. Empirical results 93
4.5.1. Deep learning performance before optimization 93
4.5.2. Hyperparameter optimization results 96
4.6. Conclusion and future work 100
4.7. Acknowledgments 101
4.8. References 101
Part 2. Applications and Socio-Economic-Global Perspectives 105
Chapter 5. AI-Assisted Agricultural Extension: Digital Learning Adoption through Rice Consultation Service for Site-Specific Fertilization in Indonesia 107
Tri MARGONO, Rimarsa Haninnakhonsa MARGONO, Triyani SUMIATI, Rinieta Sausan MARGONO and Koko KUSNANTO
5.1. Introduction 108
5.2. Conceptual and methodological foundations 109
5.2.1. Conceptual foundations 109
5.2.2. Methodological design 110
5.2.3. Analytical framework: from theory to practice 112
5.3. Results 113
5.3.1. Farmers' learning responses through AI-based extension: overview of respondent characteristics 113
5.3.2. Farmers' responses to the RCS 113
5.3.3. Correlations between farmers' characteristics and learning responses 114
5.3.4. Insights from FGDs 115
5.3.5. SWOT synthesis of AI-assisted learning adoption 115
5.3.6. Theoretical interpretation of empirical trends 116
5.3.7. Synthesis of key findings 117
5.4. Discussion 118
5.4.1. Empirical patterns and diffusion theory 119
5.4.2. Digital learning attributes and pedagogical implications 119
5.4.3. Institutional and social mediation 120
5.4.4. Theoretical and contextual synthesis 121
5.5. Strategic framework 121
5.5.1. Conceptual model 122
5.5.2. Operational strategies 122
5.5.3. SWOT integration 124
5.6. Conclusion and implications 125
5.7. References 126
Chapter 6. AI-Driven Feedback versus Human Touch: A New Frontier in ESL Writing Accuracy 129
Rizgar Qasim MAHMOOD
6.1. Introduction 129
6.2. Literature review 131
6.2.1. Theoretical framework 131
6.2.2. Teacher feedback 132
6.2.3. AI-driven feedback 133
6.2.4. AI feedback and major concerns 134
6.3. Methodology 135
6.3.1. Participants and setting 135
6.3.2. Data collection and instruments 137
6.3.3. Coding 137
6.3.4. Data analysis 138
6.4. Results 139
6.4.1. The impact of AI-driven and teacher feedback on tense accuracy in ESL learners' writing 139
6.4.2. Learners' perceptions of WCF from AI tools and teachers 142
6.5. Discussion 145
6.6. Conclusion 147
6.7. Limitations and future studies 148
6.8. Acknowledging AI tools and technologies 149
6.9. References 149
Chapter 7. Socioeconomic Transformation of Education in the Era of Industry 5.0 155
V.H. ABDULLAYEV, R.G. ABASZADE and I.X. NORMATOV
7.1. Introduction 155
7.2. Characteristics of Industry 5.0 156
7.3. Directions of socioeconomic transformation in education 158
7.3.1. Renewal of educational programs (competency-based approach) 158
7.3.2. Strengthening STEAM and digital literacy 158
7.3.3. Education aligned with SDGs 158
7.4. New skills required for Industry 5.0 158
7.5. Social impacts 159
7.5.1. Strengthening educational equality 159
7.5.2. Expansion of career opportunities 159
7.5.3. Knowledge exchange between regions 159
7.6. Integration model: university-industry-government cooperation 160
7.7. Conclusion 161
7.8. References 161
Chapter 8. The Role of AI in Virtual Experimentation and Modeling 163
R.G. ABASZADE, V.H. ABDULLAYEV and I.X. NORMATOV
8.1. Introduction 163
8.2. Methodology 166
8.2.1. Chosen approach 166
8.2.2. Building and training the AI model 166
8.2.3. Data preparation and validation methods 166
8.2.4. Description of the virtual experimentation environment 167
8.3. Results and discussion 168
8.3.1. Results of AI-enhanced virtual models 168
8.3.2. Comparison with traditional methods 168
8.3.3. Computational accuracy, time efficiency and adaptability 168
8.3.4. Examples of applications 169
8.4. Conclusion 169
8.5. References 169
Part 3. Ethics and Future Directions 171
Chapter 9. Reimagining Education through Responsible and Inclusive AI: Synthesis and Future Directions 173
El-Sayed M. EL-KENAWY
9.1. Introduction 173
9.2. Literature review 177
9.3. Discussion 182
9.4. Conclusion and future work 188
9.5. References 190
List of Authors 195
Index 199