Ifenthaler / Gibson Adoption of Data Analytics in Higher Education Learning and Teaching

1. Auflage 2020
ISBN: 978-3-030-47392-1
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 464 Seiten

Reihe: Education (R0)

The book aims to advance global knowledge and practice in applying data science to transform higher education learning and teaching to improve personalization, access and effectiveness of education for all. Currently, higher education institutions and involved stakeholders can derive multiple benefits from educational data mining and learning analytics by using different data analytics strategies to produce summative, real-time, and predictive or prescriptive insights and recommendations. Educational data mining refers to the process of extracting useful information out of a large collection of complex educational datasets while learning analytics emphasizes insights and responses to real-time learning processes based on educational information from digital learning environments, administrative systems, and social platforms. This volume provides insight into the emerging paradigms, frameworks, methods and processes of managing change to better facilitate organizational transformation toward implementation of educational data mining and learning analytics. It features current research exploring the (a) theoretical foundation and empirical evidence of the adoption of learning analytics, (b) technological infrastructure and staff capabilities required, as well as (c) case studies that describe current practices and experiences in the use of data analytics in higher education.

Autoren/Hrsg.

Ifenthaler, Dirk

Gibson, David

Inhaltsverzeichnis

1;Preface;6
2;Contents;10
3;About the Editors;20
4;no;20
5;About the Contributors;22
6;Part I: Focussing the Organisation in the Adoption Process;40
6.1;Chapter 1: Adoption of Learning Analytics;41
6.1.1;1.1 Introduction;41
6.1.2;1.2 Innovation Diffusion;42
6.1.2.1;1.2.1 Six Characteristics of an Innovation;42
6.1.2.2;1.2.2 Communication Channels;44
6.1.2.3;1.2.3 Encompassing Social Systems;44
6.1.2.4;1.2.4 Summary of Innovation Diffusion;45
6.1.3;1.3 Improving Higher Education with the Adoption of Learning Analytics;45
6.1.3.1;1.3.1 Acquiring Students;46
6.1.3.2;1.3.2 Promoting Learning;46
6.1.3.3;1.3.3 Offering Timely Relevant Content;47
6.1.3.4;1.3.4 Delivery Methods;48
6.1.3.5;1.3.5 Supporting Alumni Networks;48
6.1.3.6;1.3.6 Cases;49
6.1.3.6.1;1.3.6.1 Analytics Teams in Business Units of a University;49
6.1.3.6.2;1.3.6.2 Adoption of Learning Analytics in Challenge-Based Learning Design;50
6.1.4;1.4 Discussion and Outlook;52
6.1.5;References;54
6.2;Chapter 2: The Politics of Learning Analytics;59
6.2.1;2.1 Unfolding Scenarios;59
6.2.2;2.2 The Promises and Challenges of Big Data and Learning Analytics for Higher Education;60
6.2.3;2.3 Ethical and Legal Frameworks of Big Data and Learning Analytics;62
6.2.4;2.4 Knowledge Production: Algorithmic and Datafied Education and Its Consequences;63
6.2.4.1;2.4.1 On Algorithms and Data;64
6.2.4.2;2.4.2 On Interpretation and Contextualisation;66
6.2.4.3;2.4.3 On Communicating and Adopting a Learning Analytics Culture;67
6.2.4.4;2.4.4 On Data Reduction and Knowledge Production;68
6.2.5;2.5 Ecologies of Learning: Towards a Measured Learning Analytics;69
6.2.6;2.6 Implications for Universities Adopting Learning Analytics;69
6.2.7;References;73
6.3;Chapter 3: A Framework to Support Interdisciplinary Engagement with Learning Analytics;77
6.3.1;3.1 Introduction;77
6.3.1.1;3.1.1 What We Mean by Interdisciplinary;78
6.3.1.2;3.1.2 Big Data and Learning Analytics;78
6.3.2;3.2 Learning Analytics in Higher Education;80
6.3.2.1;3.2.1 Organizational Drivers;80
6.3.2.2;3.2.2 Classroom-Level Use of Learning Analytics;81
6.3.3;3.3 An Interdisciplinary Approach;82
6.3.3.1;3.3.1 Awareness – What Is Being Collected and Why;83
6.3.3.2;3.3.2 Access – Who Can Get to the Data;84
6.3.3.3;3.3.3 Resources – Where Is the Data Stored;85
6.3.4;3.4 Future Directions;87
6.3.5;3.5 Conclusion;88
6.3.6;References;88
6.4;Chapter 4: The Framework of Learning Analytics for Prevention, Intervention, and Postvention in E-Learning Environments;91
6.4.1;4.1 Introduction;91
6.4.1.1;4.1.1 Prevention;93
6.4.1.2;4.1.2 Intervention;94
6.4.1.3;4.1.3 Postvention;95
6.4.1.4;4.1.4 Differences Between Prevention, Intervention, and Postvention;96
6.4.2;4.2 Proposed Framework;97
6.4.2.1;4.2.1 Dropout;98
6.4.2.2;4.2.2 Avoidance of Learning Activities;100
6.4.2.3;4.2.3 Failing Learning Performance;100
6.4.2.4;4.2.4 Locus of Control;101
6.4.2.5;4.2.5 Academic Procrastination;101
6.4.3;4.3 Conclusion and Discussion;102
6.4.4;References;104
6.5;Chapter 5: The LAVA Model: Learning Analytics Meets Visual Analytics;108
6.5.1;5.1 Introduction;108
6.5.2;5.2 Human-Centered Learning Analytics;109
6.5.3;5.3 Visual Analytics;110
6.5.4;5.4 The LAVA Model;111
6.5.5;5.5 The LAVA Model in Action;113
6.5.5.1;5.5.1 Learning Activities;115
6.5.5.2;5.5.2 Data Collection;115
6.5.5.3;5.5.3 Data Storage and Pre-processing;115
6.5.5.4;5.5.4 Analysis;116
6.5.5.5;5.5.5 Visualization;116
6.5.5.6;5.5.6 Perception and Knowledge;116
6.5.5.7;5.5.7 Exploration;117
6.5.5.7.1;5.5.7.1 Goal;117
6.5.5.7.2;5.5.7.2 Question;118
6.5.5.7.3;5.5.7.3 Indicator;118
6.5.5.8;5.5.8 Action;124
6.5.6;5.6 Evaluation;124
6.5.6.1;5.6.1 Method;125
6.5.6.1.1;5.6.1.1 Setting;125
6.5.6.1.2;5.6.1.2 Participants;125
6.5.6.2;5.6.2 Usefulness;126
6.5.6.3;5.6.3 Usability;127
6.5.7;5.7 Conclusion;128
6.5.8;References;128
6.6;Chapter 6: See You at the Intersection: Bringing Together Different Approaches to Uncover Deeper Analytics Insights;131
6.6.1;6.1 Introduction;131
6.6.2;6.2 The Story So Far;132
6.6.2.1;6.2.1 Centralized Support;134
6.6.2.2;6.2.2 System Generated Reports;135
6.6.3;6.3 Research Sprints;136
6.6.3.1;6.3.1 The First Year Chemistry Curriculum;138
6.6.3.2;6.3.2 The French Language Curriculum;139
6.6.3.3;6.3.3 The Analysis of Student Course Progress;141
6.6.4;6.4 Conclusion;142
6.6.4.1;6.4.1 Future Directions;143
6.6.5;References;145
6.7;Chapter 7: “Trust the Process!”: Implementing Learning Analytics in Higher Education Institutions;148
6.7.1;7.1 Introduction;148
6.7.2;7.2 Adoption of Learning Analytics;149
6.7.2.1;7.2.1 Issues and Challenges of LA Adoption;150
6.7.2.2;7.2.2 Leadership of LA Adoption;152
6.7.2.3;7.2.3 Models of LA Adoption;153
6.7.3;7.3 Adapted Roma Model for Bottom-Up Adoption;155
6.7.4;7.4 Adoption of Learning Analytics at Aalen UAS;156
6.7.4.1;7.4.1 A Small Project as Starting Point;156
6.7.4.2;7.4.2 Closing the Gap Between Teachers and Learners;158
6.7.4.3;7.4.3 Extension to Higher Levels;160
6.7.4.4;7.4.4 Summary of the Adoption Process;161
6.7.5;7.5 Outlook and Conclusion;162
6.7.6;References;166
7;Part II: Focussing the Learner and Teacher in the Adoption Process;170
7.1;Chapter 8: Students’ Adoption of Learner Analytics;171
7.1.1;8.1 Introduction;171
7.1.2;8.2 Methodology;174
7.1.3;8.3 Results;176
7.1.3.1;8.3.1 Implementation of a Learner Analytics Platform;177
7.1.3.2;8.3.2 Adoption of Connect Analytics in the Live Pilot;178
7.1.3.2.1;8.3.2.1 Somewhat Active but Irregular Users (N = 12);180
7.1.3.2.2;8.3.2.2 Active and Regular Users (N = 6);182
7.1.3.2.3;8.3.2.3 Somewhat Active and Regular Users (N = 6);183
7.1.3.2.4;8.3.2.4 Active but Irregular Users (N = 5);183
7.1.3.2.5;8.3.2.5 Sporadics and Users with No Logging Activity (N = 49);183
7.1.3.3;8.3.3 Students’ Feedback on Connect Analytics After the Live Pilot;184
7.1.4;8.4 Discussion: Understanding Students’ Adoption of Learner Analytics;186
7.1.5;8.5 Conclusions;189
7.1.6;References;190
7.2;Chapter 9: Learning Analytics and the Measurement of Learning Engagement;193
7.2.1;9.1 Introduction;193
7.2.2;9.2 This Study;194
7.2.2.1;9.2.1 Context;195
7.2.2.2;9.2.2 Instrument and Procedure;196
7.2.2.3;9.2.3 Data Analysis;198
7.2.3;9.3 Results;198
7.2.3.1;9.3.1 Descriptive Statistics of Survey-Based Measures;198
7.2.3.2;9.3.2 Cluster-Based Learning Profiles;199
7.2.3.3;9.3.3 Learning Profiles and Course Performance;201
7.2.3.4;9.3.4 Bivariate Relationships Between Engagement Indicators and Course Performance;202
7.2.3.5;9.3.5 Multivariate Relationships Between Engagement Indicators and Course Performance;203
7.2.3.6;9.3.6 Bivariate Relationships Between Survey-Based Engagement Scores and Log-Based Engagement Indicator;204
7.2.4;9.4 Findings and Discussion;205
7.2.5;9.5 Conclusion;209
7.2.6;References;209
7.3;Chapter 10: Stakeholder Perspectives (Staff and Students) on Institution-Wide Use of Learning Analytics to Improve Learning and Teaching Outcomes;211
7.3.1;10.1 Introduction and Context;211
7.3.2;10.2 Approach;213
7.3.3;10.3 Staff Perspectives on LA;214
7.3.4;10.4 Students’ Perspectives on LA;219
7.3.5;10.5 Comparing Responses from Staff and Students – the ‘Standout’ Messages;225
7.3.5.1;10.5.1 Awareness of Learning Analytics and Data Collection;225
7.3.5.2;10.5.2 How LA Might Be Used to Support Learning;227
7.3.5.3;10.5.3 Concerns;228
7.3.5.4;10.5.4 Practical Actions for More Effective Use of LA;230
7.3.6;10.6 Conclusion;231
7.3.7;References;232
7.4;Chapter 11: How and Why Faculty Adopt Learning Analytics;235
7.4.1;11.1 Introduction;235
7.4.2;11.2 Background;236
7.4.2.1;11.2.1 Learning Analytics Implementation and Adoption: Institutions;236
7.4.2.2;11.2.2 Learning Analytics Implementation and Adoption: Teachers;237
7.4.2.3;11.2.3 Theoretical Framework – Diffusion of Innovations;239
7.4.3;11.3 Methods;240
7.4.3.1;11.3.1 Research Questions;240
7.4.3.2;11.3.2 The SRES as a LA Platform;241
7.4.3.3;11.3.3 Data Collection;244
7.4.4;11.4 Findings;245
7.4.4.1;11.4.1 Perceived Attributes of the Innovation;245
7.4.4.2;11.4.2 Relative Advantage;246
7.4.4.2.1;11.4.2.1 Compatibility;248
7.4.4.2.2;11.4.2.2 Complexity;248
7.4.4.2.3;11.4.2.3 Trialability;249
7.4.4.2.4;11.4.2.4 Observability;249
7.4.4.3;11.4.3 Communication Channels;250
7.4.5;11.5 Discussion & Conclusions;251
7.4.6;References;253
7.5;Chapter 12: Supporting Faculty Adoption of Learning Analytics within the Complex World of Higher Education;255
7.5.1;12.1 Introduction;255
7.5.1.1;12.1.1 Background;256
7.5.1.2;12.1.2 The Bay View Alliance;258
7.5.1.3;12.1.3 The Learning Analytics Research Collaborative;258
7.5.2;12.2 The Cycle of Progress for Sustainable Change;259
7.5.2.1;12.2.1 Awareness;260
7.5.2.2;12.2.2 Understanding;261
7.5.2.3;12.2.3 Action;261
7.5.2.4;12.2.4 Reflection;261
7.5.3;12.3 Methodolgy;262
7.5.4;12.4 Results;263
7.5.4.1;12.4.1 Vignettes;263
7.5.4.2;12.4.2 Cultural Change Indicators;265
7.5.4.3;12.4.3 Program Support;266
7.5.5;12.5 Discussion;267
7.5.5.1;12.5.1 Commonalities and Contrasts;267
7.5.5.2;12.5.2 Theoretical Framework;268
7.5.5.3;12.5.3 Implications and Limitations;269
7.5.5.4;12.5.4 Future Directions;270
7.5.6;12.6 Conclusion;271
7.5.7;References;272
7.6;Chapter 13: It’s All About the Intervention: Reflections on Building Staff Capacity for Using Learning Analytics to Support Student Success;274
7.6.1;13.1 Introduction;274
7.6.2;13.2 Learning Analytics;275
7.6.3;13.3 How Tutors Support Students;276
7.6.4;13.4 Enhancing the Tutoring/Advising Process Using Learning Analytics;278
7.6.4.1;13.4.1 Methodology;279
7.6.4.2;13.4.2 Case Study: Using Learning Analytics to Support Students at Nottingham Trent University;280
7.6.4.2.1;13.4.2.1 Implementation of Learning Analytics;280
7.6.4.2.2;13.4.2.2 Building Staff Capacity to Support Students Using Learning Analytics;281
7.6.5;13.5 Trigger/Prompt;281
7.6.6;13.6 Communication;282
7.6.7;13.7 Intervention;283
7.6.7.1;13.7.1 Summary for Building Staff Capacity to Support Students Using Learning Analytics;285
7.6.8;13.8 Institutional Recommendations;285
7.6.9;13.9 Conclusions;286
7.6.10;References;287
7.7;Chapter 14: Experiences in Scaling Up Learning Analytics in Blended Learning Scenarios;290
7.7.1;14.1 Introduction;290
7.7.2;14.2 Methodology;292
7.7.2.1;14.2.1 Collecting Learning Analytics Requirements;293
7.7.2.2;14.2.2 Evaluation Strategies;294
7.7.3;14.3 Scaling Up Learning Analytics;295
7.7.3.1;14.3.1 Building the Requirements;295
7.7.3.1.1;14.3.1.1 Outcome-Driven Innovation and Exploratory Data Analysis: Results;295
7.7.3.1.2;14.3.1.2 Building the Requirements: Literature Reviews;296
7.7.3.1.3;14.3.1.3 Building the Requirements: Outcomes;298
7.7.3.2;14.3.2 Institutional Regulation Preparation;299
7.7.3.3;14.3.3 Learning Analytics Services Implementation;300
7.7.3.4;14.3.4 Data Management;301
7.7.3.5;14.3.5 Analytics Engine;303
7.7.3.6;14.3.6 Results Visualization;304
7.7.4;14.4 Evaluation Strategies for LA;305
7.7.4.1;14.4.1 Study Setting;305
7.7.4.2;14.4.2 Evaluation Findings;308
7.7.5;14.5 Lessons Learned and Conclusions;310
7.7.6;References;312
8;Part III: Cases of Learning Analytics Adoption;316
8.1;Chapter 15: Building Confidence in Learning Analytics Solutions: Two Complementary Pilot Studies;317
8.1.1;15.1 Introduction;317
8.1.2;15.2 Related Works;318
8.1.3;15.3 1st Pilot Study: Mining Academic Data;320
8.1.3.1;15.3.1 Context and Goals;321
8.1.3.2;15.3.2 Graduating Versus Dropping out;322
8.1.3.3;15.3.3 Typical Completing Behaviors;324
8.1.3.4;15.3.4 Discussion;326
8.1.4;15.4 2nd Pilot Study;327
8.1.4.1;15.4.1 Context and Goals;327
8.1.4.2;15.4.2 Design of a Student-Centered Dashboard;328
8.1.4.3;15.4.3 Usability of the Dashboard;331
8.1.4.4;15.4.4 Discussion;332
8.1.5;15.5 Conclusion;333
8.1.6;References;334
8.2;Chapter 16: Leadership and Maturity: How Do They Affect Learning Analytics Adoption in Latin America?;336
8.2.1;16.1 Introduction;336
8.2.2;16.2 Methods;338
8.2.2.1;16.2.1 Research Design;338
8.2.2.2;16.2.2 Research Context;339
8.2.2.3;16.2.3 Data Collection;340
8.2.2.4;16.2.4 Data Analysis;341
8.2.3;16.3 Case Descriptions;342
8.2.3.1;16.3.1 Adoption of NoteMyProgress in PUC-Chile;342
8.2.3.2;16.3.2 Adoption of TrAC in UACh;343
8.2.3.3;16.3.3 Adoption of the Redesigned Academic Counseling System in ESPOL;346
8.2.3.4;16.3.4 Adoption of Dashboards in UCuenca;349
8.2.4;16.4 Findings of Cross-Case Analysis;352
8.2.4.1;16.4.1 Leadership;352
8.2.4.2;16.4.2 Organizational Maturity;353
8.2.5;16.5 Lessons Learned and Conclusion;354
8.2.6;References;355
8.3;Chapter 17: Adoption of Bring-Your-Own-Device Examinations and Data Analytics;358
8.3.1;17.1 Introduction;358
8.3.2;17.2 The Evolution of Digital Examinations;360
8.3.3;17.3 BYOD Examination Implementation Case Study;361
8.3.3.1;17.3.1 Infrastructure;362
8.3.3.1.1;17.3.1.1 Wi-Fi;362
8.3.3.1.2;17.3.1.2 Power;362
8.3.3.2;17.3.2 Human Factors;363
8.3.3.2.1;17.3.2.1 Students;364
8.3.3.2.1.1;17.3.2.1.1 Outcomes;364
8.3.3.2.1.2;17.3.2.1.2 Perceptions;364
8.3.3.2.1.3;17.3.2.1.3 Typing Versus Handwriting;365
8.3.3.2.1.4;17.3.2.1.4 Accessibility and Disability;365
8.3.3.2.1.5;17.3.2.1.5 Device Ownership;365
8.3.3.2.1.6;17.3.2.1.6 Promoting Adoption by Students;366
8.3.3.2.2;17.3.2.2 Administrators and Professional Staff;366
8.3.3.2.3;17.3.2.3 Academics;367
8.3.3.2.3.1;17.3.2.3.1 Exam Creation;368
8.3.3.2.3.2;17.3.2.3.2 Exam Marking;368
8.3.3.2.3.3;17.3.2.3.3 Promoting Adoption by Academic Staff;368
8.3.4;17.4 Bring-Your-Own-Device Examinations Data Analysis Case Study;369
8.3.4.1;17.4.1 Methodology;370
8.3.4.2;17.4.2 Results and Discussion;370
8.3.4.3;17.4.3 Areas for Consideration;374
8.3.5;17.5 Conclusions and the Future of Exam Analytics;376
8.3.6;References;378
8.4;Chapter 18: Experiential Learning in Labs and Multimodal Learning Analytics;380
8.4.1;18.1 Introduction;380
8.4.2;18.2 Theoretical Background;381
8.4.2.1;18.2.1 Lab-Based Learning;382
8.4.2.2;18.2.2 Experiential Learning in Laboratory-Based Learning Scenarios;383
8.4.2.3;18.2.3 Multimodal Learning Analytics;385
8.4.3;18.3 Learning Scenario Descriptions and Their Connection to Experiential Learning;387
8.4.3.1;18.3.1 RFID Measuring Cabinet at the Hochschule für Technik Stuttgart (HFT Stuttgart);387
8.4.3.1.1;18.3.1.1 Overall Goal of the Scenario;387
8.4.3.1.2;18.3.1.2 Lab Scenario;387
8.4.3.1.3;18.3.1.3 Learning Outcomes;389
8.4.3.2;18.3.2 RFID Lab at University of Parma: Experimental Construction of RSSI Curves;389
8.4.3.2.1;18.3.2.1 Overall Goal of the Scenario;389
8.4.3.2.2;18.3.2.2 Lab Scenario;390
8.4.3.2.3;18.3.2.3 Learning Outcomes;392
8.4.3.3;18.3.3 Connecting Experiential Learning to Lab Learning Scenarios;393
8.4.3.4;18.3.4 Enhancing Lab Learning Activities with Learning Analytics;394
8.4.3.5;18.3.5 Technical Infrastructure for Lab-Based Learning and MLA;397
8.4.4;18.4 Discussion and Conclusion;400
8.4.5;References;402
8.5;Chapter 19: Web Analytics as Extension for a Learning Analytics Dashboard of a Massive Open Online Platform;405
8.5.1;19.1 Introduction;405
8.5.2;19.2 Related Work;407
8.5.3;19.3 Concept of the LA Cockpit;408
8.5.3.1;19.3.1 Activity Measurement;409
8.5.3.2;19.3.2 Web Analytics;410
8.5.3.3;19.3.3 Metrics and Visualization;412
8.5.4;19.4 Implementation;412
8.5.4.1;19.4.1 Device Statistics;412
8.5.4.2;19.4.2 Activity Calendar;413
8.5.4.3;19.4.3 Heatmap;414
8.5.5;19.5 Discussion;414
8.5.5.1;19.5.1 First Evaluation Results;415
8.5.5.2;19.5.2 Limitations;416
8.5.6;19.6 Conclusion;417
8.5.7;References;419
8.6;Chapter 20: A Dimensionality Reduction Method for Time Series Analysis of Student Behavior to Predict Dropout in Massive Open Online Courses;421
8.6.1;20.1 Introduction;421
8.6.1.1;20.1.1 Research on Student Attrition Prediction in MOOCS;422
8.6.1.2;20.1.2 Clickstream Data for Prediction of Student Attrition;424
8.6.2;20.2 Related Works;425
8.6.3;20.3 Experiment;426
8.6.4;20.4 Results;429
8.6.5;20.5 Discussion;430
8.6.6;20.6 Conclusions and Implications;433
8.6.7;References;435
8.7;Chapter 21: Evidence-Based Learning Design Through Learning Analytics;437
8.7.1;21.1 Introduction;437
8.7.1.1;21.1.1 Learning Design and Learning Analytics;438
8.7.1.2;21.1.2 Course Design Archetypes;439
8.7.2;21.2 Methodology;440
8.7.3;21.3 Findings;442
8.7.3.1;21.3.1 Distribution of Archetypes at the Local Institution;443
8.7.3.2;21.3.2 Comparison Between the Analysis of the Original Data and Local Data;443
8.7.3.3;21.3.3 Consistency Between Archetypes Extracted from Analytics and Instructors’ Predictions;447
8.7.4;21.4 Discussion;450
8.7.5;References;452
9;Index;455