In this book, we primarily focus on studies that provide objective, unobtrusive, and innovative measures (e.g., indirect measures, content analysis, or analysis of trace data) of SEL skills (e.g., collaboration, creativity, persistence), relying primarily on learning analytics methods and approaches that would potentially allow for expanding the assessment of SEL skills and competencies at scale. What makes the position of learning analytics pivotal in this endeavor to redefine measurement of SEL skills are constant changes and advancements in learning environments and the quality and quantity of data collected about learners and the process of learning. Contemporary learning environments that utilize virtual and augmented reality to enhance learning opportunities accommodate for designing tasks and activities that allow learners to elicit behaviors (either in face-to-face or online context) not being captured in traditional educational settings.
Novel insights provided in the book span across diverse types of learning contexts and learner populations. Specifically, the book addresses relevant and emerging theories and frameworks (in various disciplines such as education, psychology, or workforce) that inform assessments of SEL skills and competencies. In so doing, the book maps the landscape of the novel learning analytics methods and approaches, along with their application in the SEL assessment for K-12 learners as well as adult learners. Critical to the notion of the SEL assessment are data sources. In that sense, the book outlines where and how data related to learners' 21st century skills and competencies can be measured and collected. Linking theory to data, the book further discusses tools and methods that are being used to operationalize SEL and link relevant skills and competencies with cognitive assessment. Finally, the book addresses aspects of generalizability and applicability, showing promising approaches for translating research findings into actionable insights that would inform various stakeholders (e.g., learners, instructors, administrators, policy makers).
Author(s): Yuan 'Elle' Wang, Srećko Joksimović, Maria Ofelia Z. San Pedro, Jason D. Way, John Whitmer
Series: Advances in Analytics for Learning and Teaching
Publisher: Springer
Year: 2022
Language: English
Pages: 340
City: Cham
Contents
Contributors
Chapter 1: Re-contextualizing Inclusiveness & SEL in Learning Analytics
1.1 Introduction
1.1.1 SEL
1.1.2 Recent Development of SEL & LA
1.2 SEL and Inclusiveness
1.2.1 Diversity of Success Metrics
1.2.2 Diversity of Learners
1.3 Opportunities for Inclusiveness in SEL-Focused LA Research
1.3.1 SEL Assessments at Scale Online
1.3.2 Integrating Domain-Based Education Research
1.3.3 Incorporate Diverse Learner Features
References
Chapter 2: State of the Science on Social and Emotional Learning: Frameworks, Assessment, and Developing Skills
2.1 Organizing Frameworks for Social and Emotional Skills
2.1.1 The Collaborative for Academic, Social, and Emotional Learning
2.1.2 Organisation for Economic Cooperation and Development
2.1.3 ACT Holistic Framework
2.2 SEL Frameworks Summary
2.3 Social and Emotional Skill Development
2.4 Social and Emotional Skill Assessment
2.4.1 Self-Report Likert
2.4.2 Situational Judgment Test
2.4.3 Forced Choice
2.5 Conclusion
References
Chapter 3: Mapping the Landscape of Social and Emotional Learning Analytics
3.1 Introduction
3.2 Measuring Social and Emotional Learning Skills
3.2.1 Collaboration
3.2.2 Open-Mindedness
3.2.3 Engaging with Others
3.2.4 Compound Skills
3.2.5 Task Performance
3.2.6 Emotional Regulation
3.3 Bridging Psychometrics and Learning Analytics
3.4 The Role of Design
3.5 Conclusion
References
Part I: Key SEL Attributes
Chapter 4: Empathy: How Can Technology Help Foster Its Increase Rather Than Decline in the 21st Century?
4.1 Literature Review
4.1.1 Relationship of Technology to Empathy
4.1.2 Gender and Empathy
4.1.3 Impacts in the Classroom
4.2 Measures of Empathy
4.2.1 Indicators of Empathy Based on Traditional Psychometrics
4.2.2 Examples of Validated Empathy Instruments
4.2.3 Prospects for Indicators of Empathy via Machine Learning
4.2.4 Selected Findings from Studies by the Authors
4.2.5 Empathy Norms Are Related to Culture
4.2.6 Empathy Declines Less Than Other Learning Dispositions as Grade Level Increases
4.2.7 Empathy Is Associated with Other Learning Attitudes and Dispositions
4.2.8 Measurable Differences Exist in Level of Empathy Related to Gender
4.3 Topics Warranting Additional Study
4.3.1 Placement in Learning Frameworks
4.3.2 Influence of Technologies
4.3.3 Role of Learning Analytics Systems
4.4 Conclusion
References
Chapter 5: The Role of Learning Analytics in Developing Creativity
5.1 Introduction
5.2 The Definition of Creativity
5.3 The Four Ps of Creativity
5.4 Person—Who Are the Creators?
5.5 Product—What Do They Create?
5.6 Process—How Do They Create It?
5.7 Press—Where Does the Creativity Happen?
5.8 Phase—The Stages of Creativity
5.9 Paradoxes of Creativity
5.10 The Innovation Phase Model
5.11 How Can LA Use the IPAI to Encourage Creativity?
5.12 Benefits
5.13 Limitations
5.14 Conclusion
References
Chapter 6: Using Learning Analytics to Measure Motivational and Affective Processes During Self-Regulated Learning with Advanced Learning Technologies
6.1 Introduction
6.1.1 Motivation and Affect
6.2 Measuring Motivational and Affective Processes Using Multimodal Data
6.2.1 How Can These New Techniques Be Used to Detect, Track, Model, and Foster Students’ Motivation and Affect?
6.2.2 Modeling Motivational and Affective Processes
6.3 Implications of Measuring Multimodal Motivational and Affective Processes for Researchers, Students, and Educators
6.3.1 Implications for Researchers
6.3.2 Implications for Students
6.3.3 Implications for Educators
References
Chapter 7: SR-WMS: A Typology of Self-Regulation in Writing from Multiple Sources
7.1 Introduction
7.1.1 Challenges in Multi-source Composition
7.1.2 Foundations for Modelling Multi-source Composition
7.2 Literature Review
7.2.1 Multiple Source Comprehension
7.2.2 Processes in Writing
7.2.3 Self-Regulated Learning
7.3 SR-WMS – A Typology of Self-Regulation in Writing from Multiple Sources
7.4 Learning Analytics About Processes in Multi-source Writing
7.4.1 nStudy – Software to Support Multi-source Writing
7.4.2 Example
7.4.3 Implications
References
Chapter 8: Identifying Tertiary Level Educators’ Needs and Understanding of the Collaboration Process Analytics
8.1 Introduction
8.2 Background and Previous Work
8.2.1 Teacher Evaluations of Collaboration Analytics
8.3 Specific Collaboration Analytics Investigated by the Study
8.3.1 Analytics of Collaboration as a Process (CLaP)
8.4 Methodology
8.4.1 Participants
8.4.2 Data Collection Phases
8.4.3 Data Analysis
8.5 Results
8.5.1 Participants Experiences in Online Teaching and Their Confidence in Reading Basic Visualisations
8.5.2 Evaluation of Collaboration in Online Classes
8.5.3 Educator Interpretations of Students’ Online Collaboration
8.6 Discussion
8.6.1 The Extent Tertiary-Level Educators Evaluate Their Students’ Online Collaboration and the Value of Descriptive Metrics
8.6.2 The Added Value of CLaP Analysis (IGs and CCs)
8.7 Conclusions
8.7.1 Limitations and Future Research
Appendices
Appendix 8.1: Link to the Participant Survey
Appendix 8.2: Below Are the Survey Questions We Used to Probe Discussions in the Second Half of the Workshop
References
Part II: Applications in K-12
Chapter 9: Augmented Reality (AR) for Biology Learning: A Quasi-Experiment Study with High School Students
9.1 Introduction
9.2 Related Work
9.2.1 AR in Education
9.2.2 AR in Biology Learning
9.2.3 Definition of Academic Emotion
9.3 Research Methods
9.3.1 Study Context
9.3.2 AR Learning Material
9.3.3 Procedure
9.3.4 Measures
9.3.5 Data Analysis
9.4 Results
9.4.1 Students’ Perception of AR
9.4.2 Learning Performance
9.4.3 Academic Emotion
9.5 Discussions
9.6 Limitations
9.7 Conclusions and Future Work
Appendix
AEQ ITEMS
References
Chapter 10: Struggling Readers Smiling on the Inside and Getting Correct Answers
10.1 Introduction
10.2 Related Work
10.2.1 Inclusive Learning Analytics and Universal Design for Learning
10.2.2 Emotion, Cognition, and Reading Comprehension
10.2.3 Measuring Emotion with Sentiment Analysis
10.2.4 Measuring Emotion by Self-Report
10.2.5 Measuring Reading Comprehension
10.3 The Present Study
10.3.1 Ethical Concerns with Predictive Modeling in Education
10.4 Participants
10.5 Procedure
10.6 Instruments
10.6.1 What’s Your Reaction?
10.6.2 Discuss It
10.6.3 Boost Your Understanding
10.6.4 RAPID Probability
10.7 The Dataset
10.8 Analysis
10.9 Results
10.9.1 (RQ1) to What Extent Can We Use Sentiment Analysis to Interpret Self-Report?
10.9.1.1 (RQ2) to What Extent Can We Use Sentiment Analysis to Interpret Students’ Discussion Comments?
10.9.2 (RQ3) to What Extent Does Using a Valence Interpretation of Self-Report and Discussion Comments Correlate with Providing Correct Answers in a Reading Comprehension Activity?
10.9.2.1 Sentiment of Self-Report Compared to Reading Comprehension
10.9.2.2 Sentiment of Discussion Compared with Reading Comprehension
10.9.2.3 Logistic Regression
10.10 Discussion
10.11 Implications for Practice
10.12 Acknowledgements
References
Chapter 11: Exploring Selective College Attendance and Middle School Cognitive and Non-cognitive Factors Within Computer-Based Math Learning
11.1 Social Cognitive Career Theory and Pathway to College
11.2 Cognitive and Non-cognitive Factors in Academic Settings
11.3 Educational Technology in Assessing Cognitive and Non-cognitive Factors
11.4 Methods
11.4.1 The ASSISTments System
11.4.2 Dependent Variable: College Selectivity
11.4.3 Independent Variables: Student Knowledge, Academic Emotions and Behavior from Interaction Data
11.4.4 Modeling Student Knowledge
11.4.5 Modeling Academic Emotions and Disengaged Behavior
11.4.6 Modeling College Selectivity
11.5 Results
11.5.1 Correlational Analyses
11.5.2 Differences of Predictors Between Going to a Selective College and Not Going to a Selective College
11.5.3 Logistic Regression Model of Going to a Selective College
11.6 Discussion and Conclusion
References
Part III: Applications in Adult and Professional Education
Chapter 12: Single-Case Learning Analytics to Support Social-Emotional Learning: The Case of Doctoral Education
12.1 Introduction
12.2 Related Work
12.2.1 Social and Emotional Learning (SEL) and Doctoral Education
12.2.2 Learning Analytics for Social and Emotional Learning
12.2.3 Learning Analytics for Doctoral Education
12.3 Single-Case Learning Analytics
12.4 A Simple SCLA Platform: LAPills
12.5 An Exploratory Case Study of an SCLA Intervention During the First Waves of the COVID-19 Pandemic
12.5.1 Context
12.5.2 Methods
12.5.3 Results
12.6 Cohort-Based Models of Progress
12.7 Individual (SCLA-Based) Models of Progress
12.8 Objective Performance of Cohort- and SCLA-Based Models of Progress
12.9 Discussion and Conclusions
References
Chapter 13: Investigating the Potential of AI-Based Social Matching Systems to Facilitate Social Interaction Among Online Learners
13.1 Introduction
13.2 Related Work
13.2.1 Profiling and Computing Matches for Online Learners
13.2.2 Designing Technology-Mediated Remote Social Interactions
13.2.3 Potential Challenges in Social Matching Among Online Learners
13.2.4 Summary
13.3 SAMI: Conversational Agents as Social Matching Systems
13.4 Evaluation of a Social Matching System in Online Learning
13.4.1 Social Matching Among Online Learners: Challenges and Design
13.4.2 Towards Collaborative Social Matching in Online Learning
13.5 Conclusions
References
Chapter 14: Developing Social Interaction Metrics for an Active, Social, and Case-Based Online Learning Platform
14.1 Active Learning
14.2 Social Learning Analytics
14.3 Active, Social, and Case-Based Online Learning
14.3.1 Cohort: The Primary Unit of Social Interaction
14.3.2 Some Synchrony: Common Deadlines and Locked Content
14.3.3 Shared Reflections/Polls/Cold Calls
14.3.4 Peer Help
14.3.5 Activity Feed, Map, Directory, and Shared Articles
14.3.6 Course-Specific Group Activities
14.3.7 Grading, Completion, and Credential vs. Certificate
14.4 Social Interaction Metric Definitions
14.5 Social Interaction Metric Measurements
14.6 Conclusion
14.7 Future Work
References
Chapter 15: Network Climate Action Through MOOCs
15.1 Introduction
15.2 Literature Review
15.3 Methods
15.3.1 Online Course and Participants
15.3.2 Data Collection and Analysis
15.4 Results
15.4.1 Climate Actions
15.4.2 Networks
15.4.3 Strategies to Influence Networks
15.4.3.1 Social Norms
15.4.3.2 Social Mobilization
15.4.3.3 Spread of Complex Behavior
15.4.3.4 Social Marketing
15.4.3.5 Social Media
15.5 Discussion
15.6 Limitations
15.7 Conclusion
Appendix
Post Survey
References
Index
