Chapter 11 Novel Derivation and Application of Skill Matrices: The q-Matrix Method
Contents
11.1 Introduction
11.2 Relation to Prior Work
11.3 Method
11.4 Comparing Expert and Extracted
11.4.1 Binary Relations Tutorial, Section 1 (BRT-1)
11.4.2 Binary Relations Tutorial, Section 2 (BRT-2)
11.4.3 Binary Relations Tutorial, Section 3 (BRT-3)
11.4.4 How Many Concepts and How Much Data?
11.4.5 Summary of Expert-Extracted Comparison
11.5 Evaluating Remediation
11.6 Conclusions
References
Chapter 12 Educational Data Mining to Support Group Work in Software Development Projects
Chapter 13 Multi-Instance Learning versus Single-Instance Learning for Predicting the Student’s Performance
Contents
13.1 Introduction
13.2 Multi- Instance Learning
13.3 Problem of Predicting Students' Results Based on Their Virtual Learning Platform Performance
13.4 Experimentation and Results
13.4.1 Problem Domain Used in Experimentation
13.4.2 Comparison with Supervised Learning Algorithms
13.4.3 Comparison with Multi- Instance Learning
13.4.4 Comparison between Single- and Multi- Instance Learning
13.5 Conclusions and Future Work
References
Chapter 14 A Response-Time Model for Bottom-Out Hints as Worked Examples
Chapter 15 Automatic Recognition of Learner Types in Exploratory Learning Environments
Contents
15.1 Introduction
15.2 Related Work
15.3 The AIspace CSP Applet Learning Environment
15.4 Off- Line Clustering
15.5 Online Recognition
15.6 Conclusions and Future Work
References
Chapter 16 Modeling Affect by Mining Students’ Interactions within Learning Environments
Chapter 17 Measuring Correlation of Strong Symmetric Association Rules in Educational Data
Chapter 18 Data Mining for Contextual Educational Recommendation and Evaluation Strategies
Contents
18.1 Introduction
18.2 Data Mining in Educational Recommendation
18.3 Contextual Paper Recommendation with Multidimensional Nearest- Neighbor Approach
18.4 Empirical Studies and Results
18.5 Concluding Remarks
References
Chapter 19 Link Recommendation in E-Learning Systems
Based on Content-Based Student Profiles
Chapter 20 Log-Based Assessment of Motivationin Online Learning
Chapter 21 Mining Student Discussions for Profiling Participation and Scaffolding Learning
Contents
21.1 Introduction
21.2 Developing Scaffolding Capability: Mining Useful Information from Past Discussions
21.2.1 Step 1: Discussion Corpus Processing
21.2.2 Step 2: Technical Term Processing
21.2.3 Step 3: Term Vector Generation
21.2.4 Step 4: Term Weight Computation
21.2.5 Step 5: Similarity Computation and Result Generation
21.2.6 Step 6: Evaluation of System Responses
21.3 Profiling Student Participation with Gender Data and Speech Act Classifiers
21.3.1 Speech Act Classifiers
21.3.2 Gender Classifier/ Distribution
21.3.3 An Application of Gender Classifier/ Distribution
21.4 Related Work
21.5 Summary and Discussion
References
Chapter 22 Analysis of Log Data from a Web-Based Learning Environment: A Case Study
Chapter 23 Bayesian Networks and Linear Regression Models of Students’ Goals, Moods, and Emotions
Chapter 24 Capturing and Analyzing Student Behavior in a Virtual Learning Environment: A Case Study on Usage of Library Resources
Chapter 25 Anticipating Students’ Failure As Soon As Possible
Chapter 26 Using Decision Trees for Improving AEH Courses
Chapter 27 Validation Issues in Educational Data Mining: The Case of HTML-Tutor and iHelp
Contents
27.1 Introduction
27.2 Validation in the Context of EDM
27.3 Disengagement Detection Validation: A Case Study
27.3.1 Detection of Motivational Aspects in e- Learning
27.3.2 Proposed Approach to Disengagement Detection
27.3.3 Disengagement Detection Validation
27.3.3.1 Data Considerations
27.3.3.2 Annotation of the Level of Engagement
27.3.3.3 Analysis and Results
27.3.3.4 Cross- System Results Comparison
27.4 Challenges and Lessons Learned
27.5 Conclusions
References
Chapter 28 Lessons from Project LISTEN’s Session Browser
Contents
28.1 Introduction
28.1.1 Relation to Prior Research
28.1.2 Guidelines for Logging Tutorial Interactions
28.1.2.1 Log Tutor Data Directly to a Database
28.1.2.2 Design Databases to Support Aggregation across Sites
28.1.2.3 Log Each School Year's Data to a Different Database
28.1.2.4 Include Computer, Student ID, and Start Time as Standard Fields
28.1.2.5 Log End Time as well as Start Time
28.1.2.6 Name Standard Fields Consistently Within and Across Databases
28.1.2.7 Use a Separate Table for Each Type of Tutorial Event
28.1.2.8 Index Event Tables by Computer, Student ID, and Start Time
28.1.2.9 Include a Field for the Parent Event Start Time
28.1.2.10 Logging the Nonoccurrence of an Event Is Tricky
28.1.3 Requirements for Browsing Tutorial Interactions
28.2 Specify a Phenomenon to Explore
28.2.1 Specify Events by When They Occurred
28.2.2 Specify Events by a Database Query
28.2.3 Specify Events by Their Similarity to Another Event
28.3 Display Selected Events with the Context in Which They Occurred, in Adjustable Detail
28.4 Summarize Events in Human- Understandable Form
28.5 Adapt Easily to New Tutor Versions, Tasks, and Researchers
28.5.1 Input Meta- Data to Describe Database Structure
28.5.2 Which Events to Include
28.5.3 Make Event Summaries Customizable by Making Them Queries
28.5.4 Loadable Configurations
28.6 Conclusion
Acknowledgments
References
Chapter 29 Using Fine-Grained Skill Models to Fit Student Performance with Bayesian Networks
Chapter 30 Mining for Patterns of Incorrect Response in Diagnostic Assessment Data
Contents
30.1 Introduction
30.2 The DIAGNOSER
30.3 Method
30.4 Results
30.5 Discussion
References
Chapter 31 Machine-Learning Assessment of Students’ Behavior within Interactive Learning Environments
Chapter 32 Learning Procedural Knowledge from User Solutions to Ill-Defined Tasks in a Simulated Robotic Manipulator
Contents
32.1 Introduction
32.2 The CanadarmTutor Tutoring System
32.3 A Domain Knowledge Discovery Approach for the Acquisition of Domain Expertise
32.3.1 Step 1: Recording Users' Plans
32.3.2 Step 2: Mining a Partial Task Model from Users' Plans
32.3.3 Step 3: Exploiting the Partial Task Model to Provide Relevant Tutoring Services
32.3.3.1 Assessing the Profile of a Learner
32.3.3.2 Guiding the Learner
32.3.3.3 Letting Learners Explore Different Ways of Solving Problems
32.4 Evaluating the New Version of CanadarmTutor
32.5 Related Work
32.6 Conclusion
Acknowledgments
References
Chapter 33 Using Markov Decision Processes for Automatic Hint Generation
Chapter 34 Data Mining Learning Objects
Contents
34.1 Introduction
34.2 Introduction: Formulation, Learning Objects
34.3 Data Sources in Learning Objects
34.4 The Learning Object Management System AGORA
34.5 Methodology
34.6 Conclusions
Acknowledgments
References
Chapter 35 An Adaptive Bayesian Student Model for Discovering the Student’s Learning Style and Preferences
Contents
35.1 Introduction
35.2 The Learning Style Model
35.3 The Decision Model
35.4 Selecting the Suitable Learning Objects
35.5 Conclusions and Future Work
References