Analytics in Action - Education
1 like126 views
This document discusses learning analytics and its use in higher education. It defines learning analytics as using data, analysis, and predictive modeling to improve teaching and learning. This is done by aggregating student data from various systems to gain insights into academic performance and identify at-risk students. Examples are given of universities that have implemented learning analytics to increase graduation rates and student persistence. Challenges discussed include issues with data integration and privacy, and ensuring analytics are used appropriately. The future of learning analytics is predicted to include more data sources and standards to better support personalized learning.
Analytics in Action - Education
- 1. Analytics in Action http://DSign4.education Higher Education February 2019
- 2. Introduction ©2016 L. SCHLENKER Agenda Introduction Definitions Infrastructure Use Scenarios Limits
- 4. Education Telecommunications Textiles Medicine Leisure Automobile Separation, alignment, cohesion Leading the flock Challenges
- 5. • Segment, Qualify, Develop, Measure • What is the business model here? • Three possible markets – learning, networking, recognition • How can we use digital technologies to improve the business model? • How do we measure success? University Business Model Technology
- 6. • The use of data, analysis, and predictive modeling to improve teaching and learning • Analytics models aggregate data in new ways • Help students and institutions understand past, present and future academic performance • Impact on personalized learning, pedagogical practices, curriculum development, institutional planning, and research Learning Analytics Technology Learning Analytics: Challenges and Future Research
- 7. • Based on multiple dimensions of a learner’s activities, including attendance and participation in class, in co-curricular activities • Data might reside in any number of repositories, such as LMSs, learning tools, and the institution’s student information system • Applying models and algorithms designed to produce actionable findings • Impact on personalized learning, pedagogical practices, curriculum development, institutional planning, and research How does it work? Technology
- 8. • The input layer that provides the infrastructure with the data and the activities. • The data layer –which is for storing student activities carried out in the various online learning environments (LRS) • The business layer, which aggregates, organizes, analyses and customizes personal data • The presentation layer, which provide teachers and students insights into study behavior Data Infrastructure Technology confluence.sakaiproject.org How to start with learning analytics?
- 9. • Georgia State University tailored individual interventions to narrow the graduation gap for low- income, first-generation, and minority students • San Diego State University’s Instructional Technology Servicesgoal to identify and intervene with students who were at-risk of failing • University of Central Florida, an Analytics Insights and Action Team helps increase undergraduate persistence by synthesizing insights from various analytics tools and developing processes that identify at-risk student • Digital Innovation Greenhouse at the University of Michigan works with user communities to adopt wider use of digital engagement tools like E-Coach, a tool that personalizes learning for students in large classes Whose doing it? Technology
- 10. • identify which students are not learning effectively and intervene to improve the their educational trajectory • help students find which academic paths are best suited to their interests and capitalize on their individual strength • map their academic progress in near-real time, without waiting for midterms or final exams, and can inspire them to take a more active role in their learning • Data gleaned from analytics might help institutions design better courses and make better use of learning resources such as faculty talent What is the bottom line? Technology
- 11. • Proxies of learning - it can be tempting to mistake correlations for causation • Requires close cooperation between campus departments that traditionally have worked independently (e.g., IT, academic affairs, student affairs, and faculty). • Distributed across campus the data is difficult to integrate, particularly if technology vendors format data in proprietary ways • Ethical issues surrounding data privacy and institutional obligations to act on analytics findings, including by providing resources to assist those learners • Misapprehensions about analytics among university administrators can result in unrealistic expectations for resultts What are the risks? Technology
- 12. • From an optional feature to a required component of academic technologies • Integration of disparate data sets from a broader range of sources, including the Internet of Things • Evolving learning data standards (e.g., xAPI and Caliper) may make it possible to aggregate much more learning data • applications such as the LMS will increasingly be judged on how well they integrate with or provide learning analytics What does the future hold ? Technology
- 13. • Virani K., (2016) Data-driven Education (video) • Chatti, M., (2016), Learning Analytics: Challenges and Future Research • De Wit et al., (2016?) How to start with learning analytics? • Smith K.,(2016) Predictive Analytics: Nudging, Shoving, and Smacking Behaviors in Higher Education • Fritz J. and Whitmore J., (2017) Moving the Heart and Head Bibliography Next Steps
- 14. • What is the organization’s business model? • Why does the organization focus on data? • How is the Data Science team organized? • Which data science techniques does the organization favor ? • What is the link between data science and decision making? • How does the organization use Data Science to propel growth Case Study Questions Technology