This book illustrates the design, development, and evaluation of personalized intelligent tutoring systems that emulate human cognitive intelligence by incorporating artificial intelligence. Artificial intelligence is an advanced field of research. It is particularly used in the field of education to increase the effectiveness of teaching and learning techniques. With the advancement of internet technology, there is a rapid growth in web based distance learning modality. This mode of learning is better known as the e-learning system. These systems present low intelligence because they offer a pre-identified learning frame to their learners. The advantage of these systems is to offer to learn anytime and anyplace without putting emphasis on a learner's needs, competency level, and previous knowledge. Every learner has different grasping levels, previous knowledge, and preferred mode of learning, and hence, the learning process of one individual may significantly vary from other individuals.
This book provides a complete reference for students, researchers, and industry practitioners interested in keeping abreast of recent advancements in this field. It encompasses cognitive intelligence and artificial intelligence which are very important for deriving a roadmap for future research on intelligent systems.
Author(s): Ninni Singh, Vinit Kumar Gunjan, Jacek M. Zurada
Series: Advanced Technologies and Societal Change
Publisher: Springer
Year: 2022
Language: English
Pages: 187
City: Singapore
Preface
Contents
1 Introduction
1.1 Introduction
1.2 Need of an Intelligent Tutoring System
1.3 A Growing Field Intelligent Tutoring System
1.4 Effectiveness of ITS
1.5 Intelligent Tutoring System Architecture
1.5.1 Learner Model
1.5.2 Pedagogy Model
1.5.3 Domain Model
1.5.4 Expert Model
1.5.5 Learner Interface
1.6 Book Contributions
1.6.1 Development of Adaptive Knowledge Base
1.6.2 Learner-Centric Curriculum Recommendation
1.6.3 Personalized Tutoring Strategy
1.6.4 Identification of Learner Understand-Ability
1.6.5 Identification of Learner Emotional State
1.7 Organization of Content
References
2 Domain Modeling
2.1 Introduction
2.2 An Epistemological Outlook Related to Domain Knowledge
2.3 Preliminary Research on Domain Model in IT
2.3.1 The Black Box Models
2.3.2 The Glass Box Models
2.3.3 The Cognitive Models
2.4 Experiential (Tacit Domain Knowledge)
2.5 Experiential Knowledge Acquisition Approaches
2.5.1 Cognitive Map
2.5.2 Causal Map
2.5.3 Self-Q
2.5.4 Semi-Structured
2.6 Ontology Engineering
2.7 Building Domain Ontologies from Texts
2.7.1 Concept Extraction
2.7.2 Attribute Extraction
2.7.3 Taxonomy Extraction
2.7.4 Conceptual Relationship Extraction
2.7.5 Instance Extraction
2.7.6 Axioms Extraction
2.8 Summary
References
3 Pedagogy Modeling
3.1 Introduction to Pedagogy Model
3.2 Preliminary Research on Pedagogy Model in ITS
3.2.1 Open Education System
3.2.2 Massive Online Open Courses
3.3 Path Sequencing of Learning Material in Learning Systems
3.4 Impact of Emotion Capturing in Learning System
3.4.1 Emotion Recognition in Learning System
3.5 Summary
References
4 Building SeisTutor Intelligent Tutoring System for Experimental Learning Domain
4.1 Introduction
4.2 Seismic Data Interpretation: As Experiential Learning Domain
4.3 Development of Adaptive Domain Model
4.3.1 Phase 1: Tacit Knowledge Acquisition and Characterization
4.3.2 Phase 2: Knowledge Representation: Multilevel Hierarchical Model
4.4 Summary
References
5 Pedagogy Modeling for Building SeisTutor Intelligent Tutoring System
5.1 Introduction
5.2 Workflow of SeisTutor
5.2.1 Development of Custom-Tailored Curriculum
5.2.2 Development of Tutoring Strategy Recommendation
5.2.3 CNN-Based Emotion Recognition Model
5.2.4 Development of Performance Analyzer Model
5.3 Summary
References
6 Execution of Developed Intelligent Tutoring System
6.1 Implementation of a System
6.2 Learner Interface Model
6.2.1 Learner Registration
6.3 Domain Model
6.4 Learner Model
6.5 Pedagogy Model
6.5.1 Performance Analyzer Model
6.6 Learner Statistics
6.7 Learner Feedback
6.8 Summary
References
7 Performance Metrics: Intelligent Tutoring System
7.1 Overview
7.2 Learner Statistics
7.2.1 Data Preparation
7.2.2 Min-Max Normalization
7.3 Learner Performance Metrics
7.3.1 Pretutoring and Post-Tutoring Performance
7.3.2 Predictive Statistical Analysis of Degree of Understanding Module
7.3.3 Kirkpatrick Four Stage Evaluation (Second Aspects of Evaluation)
7.4 SeisTutor: A Comparative Analysis with Teachable, My-Moodle and Course-Builder Learning Management System
7.4.1 My-Moodle
7.4.2 Course-Builder
7.4.3 Teachable
7.4.4 SeisTutor
7.5 Summary
References
8 Analysis of Performance Metrics
8.1 Critical Analysis of Performance Metrics
8.2 Statistical Analysis of Learner Engagement
8.3 Pretutoring and Post-tutoring Performance
8.4 Learner Learning Analysis Using Evaluation Model “Kirkpatrick”
8.4.1 Kirkpatrick Phase 1: Evaluation of Reaction
8.4.2 Kirkpatrick Phase 2: Evaluation of Learning
8.4.3 Kirkpatrick Phase 3: Evaluation of Behavior:
8.4.4 Kirkpatrick Phase 4: Evaluation of Results
8.5 Comparative Analysis of Performance Between the Learner-Centric Tutoring System “SeisTutor” with Existing Online Tutoring System
8.6 Conclusion and Future Scope
8.6.1 Summary
8.6.2 Conclusion
8.6.3 Future Scope
References
Appendix A
Appendix B
