The Many Faces of Learning Analytics: Adaptive Learning and Teaching at CSU Simon Welsh Manager, Adaptive Learning and Teaching Services Division of Student Learning Charles Sturt University E: siwelsh@csu.edu.au
Contents What is Adaptive Learning and Teaching? Data-Informed Practice Personalised Support Personalised Learning
1. What is Adaptive Learning and Teaching? Adaptive Learning and Teaching is comprised of three elements: Data-informed practice – using learning and teaching data/analytics to inform decision-making, reflective practice in teaching and design, and management of quality standards Personalised support – using analytics to support students and their learning in targeted ways through evidence-based interventions and feedback Personalised learning – using analytics-based technologies to personalise or differentiate learning experiences
1. What is Adaptive Learning and Teaching? Technology Capability Culture
2. Data-Informed Practice Three elements: Summative learning and teaching data (academic analytics) – enrolments, progress, attrition: CSU BI Strategy and Data Warehouse Course Health Dashboard, School/Faculty Reviews Evaluative feedback – formative and summative student evaluations, peer reviews, assessment & moderation processes: Challenge: how to connect these pieces and the role of Learning Analytics in evaluation (if any?)
2. Data-Informed Practice Three elements: In process learning and teaching data – variety of measures aligned to quality standards that enable management of emerging issues: Analytics include assignment returns, QA and publication of Subject Outlines, teacher-student communication in online learning environment Challenge: data and reporting systems Challenge: indicators vs direct measures
3. Personalised Support Who needs support? Four definitions of “At Risk” Locus of Risk Focus of Analytic Model Subject-level Course-level Engagement (quality of learning and achievement) At Risk of Disengagement At Risk of Exclusion Attrition At Risk of Subject Withdrawal At Risk of Attrition
3. Personalised Support Which analytics? Depends which way you slice it Challenge: consistent processes and communication Locus of Risk Focus of Analytic Model Subject-level Course-level Engagement Blackboard Analytics – integrated reports and Retention Centre Formative and summative assessments Learning activities (e.g. forum posts) Blackboard Analytics – bespoke reports and dashboards Attrition Early formative assessment tasks Priority Contact List
4. Personalised Learning Typical institutional approaches to Learning Analytics would not deliver the kind of personalised learning we sought Engagement defined in behavioural terms: the Boxer Response vs Adaptation During Learning Recognise Learning Analytics as a learning design challenge to create representations of knowledge and embed analytics in formative feedback processes Adaptation (of learning activities and feedback) during learning through analysis of knowledge representations and a students’ digital footprint Need to go beyond current adaptive learning approaches and support a wider range of pedagogies
Thanks Simon Welsh Manager, Adaptive Learning and Teaching Services Division of Student Learning Charles Sturt University E: siwelsh@csu.edu.au