Description
Book SynopsisAddresses the impacts of data mining on education and reviews applications in educational research teaching, and learning
This book discusses the insights, challenges, issues, expectations, and practical implementation of data mining (DM) within educational mandates. Initial series of chapters offer a general overview of DM, Learning Analytics (LA), and data collection models in the context of educational research, while also defining and discussing data mining's four guiding principles prediction, clustering, rule association, and outlier detection. The next series of chapters showcase the pedagogical applications of Educational Data Mining (EDM) and feature case studies drawn from Business, Humanities, Health Sciences, Linguistics, and Physical Sciences education that serve to highlight the successes and some of the limitations of data mining research applications in educational settings. The remaining chapters focus exclusively on EDM's emerging role in helping to a
Table of Contents
Notes on Contributors xi
Introduction: Education At Computational Crossroads xxiii
Samira ElAtia, Donald Ipperciel, and Osmar R. Zaïane
Part I At The Intersection of Two Fields: EDM 1
Chapter 1 Educational Process Mining: A Tutorial and Case Study Using Moodle Data Sets 3
Cristóbal Romero, Rebeca Cerezo, Alejandro Bogarín, and Miguel Sanchez‐Santillán
1.1 Background 5
1.2 Data Description and Preparation 7
1.2.1 Preprocessing Log Data 7
1.2.2 Clustering Approach for Grouping Log Data 11
1.3 Working with ProM 16
1.3.1 Discovered Models 19
1.3.2 Analysis of the Models’ Performance 23
1.4 Conclusion 26
Acknowledgments 27
References 27
Chapter 2 On Big Data And Text Mining in the Humanities29
Geoffrey Rockwell and Bettina Berendt
2.1 Busa and the Digital Text 30
2.2 Thesaurus Linguae Graecae and the Ibycus Computer as Infrastructure 32
2.2.1 Complete Data Sets 33
2.3 Cooking with Statistics 35
2.4 Conclusions 37
References 38
Chapter 3 Finding Predictors in Higher Education41
David Eubanks, William Evers Jr., and Nancy Smith
3.1 Contrasting Traditional and Computational Methods 42
3.2 Predictors and Data Exploration 45
3.3 Data Mining Application: An Example 50
3.4 Conclusions 52
References 53
Chapter 4 Educational Data Mining: A MOOC Experience55
Ryan S. Baker, Yuan Wang, Luc Paquette, Vincent Aleven, Octav Popescu, Jonathan Sewall, Carolyn Rosé, Gaurav Singh Tomar, Oliver Ferschke, Jing Zhang, Michael J. Cennamo, Stephanie Ogden, Therese Condit, José Diaz, Scott Crossley, Danielle S. McNamara, Denise K. Comer, Collin F. Lynch, Rebecca Brown, Tiffany Barnes, and Yoav Bergner
4.1 Big Data in Education: The Course 55
4.1.1 Iteration 1: Coursera 55
4.1.2 Iteration 2: edX 56
4.2 Cognitive Tutor Authoring Tools 57
4.3 Bazaar 58
4.4 Walkthrough 58
4.4.1 Course Content 58
4.4.2 Research on BDEMOOC 61
4.5 Conclusion 65
Acknowledgments 65
References 65
Chapter 5 Data Mining and Action Research 67
Ellina Chernobilsky, Edith Ries, and Joanne Jasmine
5.1 Process 69
5.2 Design Methodology 71
5.3 Analysis and Interpretation of Data 72
5.3.1 Quantitative Data Analysis and Interpretation 73
5.3.2 Qualitative Data Analysis and Interpretation 74
5.4 Challenges 75
5.5 Ethics 76
5.6 Role of Administration in the Data Collection Process 76
5.7 Conclusion 77
References 77
Part II Pedagogical Applications of EDM79
Chapter 6 Design of an Adaptive Learning System and Educational Data Mining81
Zhiyong Liu and Nick Cercone
6.1 Dimensionalities of the User Model in ALS 83
6.2 Collecting Data for ALS 85
6.3 Data Mining in ALS 86
6.3.1 Data Mining for User Modeling 87
6.3.2 Data Mining for Knowledge Discovery 88
6.4 ALS Model and Function Analyzing 90
6.4.1 Introduction of Module Functions 90
6.4.2 Analyzing the Workflow 93
6.5 Future Works 94
6.6 Conclusions 94
Acknowledgment 95
References 95
Chapter 7 The “Geometry” of Naive Bayes: Teaching Probabilities by “Drawing” Them99
Giorgio Maria Di Nunzio
7.1 Introduction 99
7.1.1 Main Contribution 100
7.1.2 Related Works 101
7.2 The Geometry of NB Classification 102
7.2.1 Mathematical Notation 102
7.2.2 Bayesian Decision Theory 103
7.3 Two-Dimensional Probabilities 105
7.3.1 Working with Likelihoods and Priors Only 107
7.3.2 De‐normalizing Probabilities 108
7.3.3 NB Approach 109
7.3.4 Bernoulli Naïve Bayes 110
7.4 A New Decision Line: Far from the Origin 111
7.4.1 De‐normalization Makes (Some) Problems Linearly Separable 112
7.5 Likelihood Spaces, When Logarithms make a Difference (or a SUM) 114
7.5.1 De‐normalization Makes (Some) Problems Linearly Separable 115
7.5.2 A New Decision in Likelihood Spaces 116
7.5.3 A Real Case Scenario: Text Categorization 117
7.6 Final Remarks 118
References 119
Chapter 8 Examining the Learning Networks of a MOOC121
Meaghan Brugha and Jean‐Paul Restoule
8.1 Review of Literature 122
8.2 Course Context 124
8.3 Results and Discussion 125
8.4 Recommendations for Future Research 133
8.5 Conclusions 134
References 135
Chapter 9 Exploring the Usefulness of Adaptive ELearning Laboratory Environments in Teaching Medical Science139
Thuan Thai and Patsie Polly
9.1 Introduction 139
9.2 Software for Learning and Teaching 141
9.2.1 Reflective Practice: ePortfolio 141
9.2.2 Online Quizzes 143
9.2.3 Online Practical Lessons 144
9.2.4 Virtual Laboratories 145
9.2.5 The Gene Suite 147
9.3 Potential Limitations 152
9.4 Conclusion 153
Acknowledgments 153
References 154
Chapter 10 Investigating Co‐Occurrence Patterns of Learners’ Grammatical Errors across Proficiency Levels and Essay Topics Based on Association Analysis 157
Yutaka Ishii
10.1 Introduction 157
10.1.1 The Relationship between Data Mining and Educational Research 157
10.1.2 English Writing Instruction in the Japanese Context 158
10.2 Literature Review 159
10.3 Method 160
10.3.1 Konan‐JIEM Learner Corpus 160
10.3.2 Association Analysis 162
10.4 Experiment 1 162
10.5 Experiment 2 163
10.6 Discussion and Conclusion 164
Appendix A: Example of Learner’s Essay (University Life) 164
Appendix B: Support Values of all Topics 165
Appendix C: Support Values of Advanced, Intermediate, and Beginner Levels of Learners 168
References 169
Part III EDM and Educational Research 173
Chapter 11 Mining Learning Sequences in MOOCs: Does Course Design Constrain Students’ Behaviors Or Do Students Shape Their Own Learning? 175
Lorenzo Vigentini, Simon McIntyre, Negin Mirriahi, and Dennis Alonzo
11.1 Introduction 175
11.1.1 Perceptions and Challenges of MOOC Design 176
11.1.2 What Do We Know About Participants’ Navigation: Choice and Control 177
11.2 Data Mining in MOOCs: Related Work 178
11.2.1 Setting the Hypotheses 179
11.3 The Design and Intent of the LTTO MOOC 180
11.3.1 Course Grading and Certification 183
11.3.2 Delivering the Course 183
11.3.3 Operationalize Engagement, Personal Success, and Course Success in LTTO 184
11.4 Data Analysis 184
11.4.1 Approaches to Process the Data Sources 185
11.4.2 LTTO in Numbers 186
11.4.3 Characterizing Patterns of Completion and Achievement 186
11.4.4 Redefining Participation and Engagement 189
11.5 Mining Behaviors and Intents 191
11.5.1 Participants’ Intent and Behaviors: A Classification Model 191
11.5.2 Natural Clustering Based on Behaviors 194
11.5.3 Stated Intents and Behaviors: Are They Related? 198
11.6 Closing the Loop: Informing Pedagogy and Course Enhancement 198
11.6.1 Conclusions, Lessons Learnt, and Future Directions 200
References 201
Chapter 12 Understanding Communication Patterns in MOOCs: Combining Data Mining and Qualitative Methods 207
Rebecca Eynon, Isis Hjorth, Taha Yasseri, and Nabeel Gillani
12.1 Introduction 207
12.2 Methodological Approaches to Understanding Communication Patterns in MOOCs 209
12.3 Description 210
12.3.1 Structural Connections 211
12.4 Examining Dialogue 213
12.5 Interpretative Models 214
12.6 Understanding Experience 215
12.7 Experimentation 216
12.8 Future Research 217
References 218
Chapter 13 An Example of Data Mining: Exploring The Relationship Between Applicant Attributes and Academic Measures of Success in a Pharmacy Program 223
Dion Brocks and Ken Cor
13.1 Introduction 223
13.2 Methods 225
13.3 Results 228
13.4 Discussion 230
13.4.1 Prerequisite Predictors 230
13.4.2 Demographic Predictors 232
13.5 Conclusion 234
Appendix A 234
References 236
Chapter 14 A New Way of Seeing: Using a Data Mining Approach to Understand Children’s Views of Diversity and “Difference” in Picture Books237
Robin A. Moeller and Hsin‐liang Chen
14.1 Introduction 237
14.2 Study 1: Using Data Mining to Better Understand Perceptions of Race 238
14.2.1 Background 238
14.2.2 Research Questions 239
14.2.3 Methods 240
14.2.4 Findings 240
14.2.5 Discussion 248
14.3 Study 2: Translating Data Mining Results to Picture Book Concepts of “Difference” 248
14.3.1 Background 248
14.3.2 Research Questions 249
14.3.3 Methodology 250
14.3.4 Findings 250
14.3.5 Discussion and Implications 252
14.4 Conclusions 252
References 252
Chapter 15 Data Mining with Natural Language Processing and Corpus Linguistics: Unlocking Access to School Children’s Language in Diverse Contexts to Improve Instructional and Assessment Practices255
Alison L. Bailey, Anne Blackstock‐Bernstein, Eve Ryan, and Despina Pitsoulakis
15.1 Introduction 255
15.2 Identifying the Problem 256
15.3 Use of Corpora and Technology in Language Instruction and Assessment 261
15.3.1 Language Corpora in ESL and EFL Teaching and Learning 261
15.3.2 Previous Extensions of Corpus Linguistics to School‐Age Language 262
15.3.3 Corpus Linguistics in Language Assessment 263
15.3.4 Big Data Purposes, Techniques, and Technology 264
15.4 Creating a School‐Age Learner Corpus and Digital Data Analytics System 266
15.4.1 Language Measures Included in DRGON 267
15.4.2 The DLLP as a Promising Practice 268
15.5 Next Steps, “Modest Data,” and Closing Remarks 269
Acknowledgments 271
Appendix A: Examples of Oral and Written Explanation Elicitation Prompts 272
References 272
Index 277
