Using Data Science to Increase Student Success in Online Education

Concurrent Session 4
Streamed Session

Watch This Session

Brief Abstract

Data has been called “the new oil” and online education generates substantial data reserves.  We will discuss several applied research projects using data science for student success, including qualitative studies and statistical modeling of social-emotional learning.  The results indicate not only what *can* be done, but what *should* be done.

Presenters

Lead Presenter: John Whitmer, ACT

John is the Senior Director for Data Science and Analytics for ACT, Inc. In this role, he leads a team of data scientists, psychometricians, and learning analytics researchers to conduct foundational research and to develop operational algorithms. These algorithms are embedded within ACT products and also power partner institutions and application. Prior to joining ACT, John led learning analytics research and development at Blackboard, the educational technology company and also led large-scale educational technology initiatives for the Chancellor's Office for the California State University and California Community Colleges. Underlying this technology work is a commitment to serving underserved and marginalized students. John holds a Doctorate in Educational Leadership from UC Davis and a Master's Degree in Sociocultural Anthropology from UC Davis.

Co-presenter: John Fritz, University of Maryland - Baltimore County

John Fritz is Associate Vice President for Instructional Technology in the University of Maryland, Baltimore County Division of Information Technology. He is responsible for UMBC's focused efforts in teaching, learning and technology, including learning analytics. He is also responsible for tier 1 (basic) user support including knowledge management. John is a frequent presenter and author for Educause events and publications, and holds a Ph.D. in Language, Literacy and Culture from UMBC.

Co-presenter: Deborah West, Flinders University

Deborah West is Pro Vice Chancellor (Learning and Teaching Innovation) at Flinders University. With a disciplinary background in social work, her research has encompassed both her discipline and learning and teaching. In recent years, her focus has been on the use of technology to support learning and teaching and in particular learning analytics and has published extensively in this field. Operationally, she has been very involved in the development of learning analytics at Charles Darwin University where she was Director of Learning and Teaching and is now applying this experience to the Flinders University environment. As PVC (Learning and Teaching Innovation) she oversees the Centre for Innovation in Learning and Teaching at Flinders University. Her portfolio includes education quality, academic development, online learning and teaching Support, work integrated learning professional support, careers and employability, student academic language and literacy support and enabling and transition programs. ORCHID ID: http://orcid.org/0000-0002-2113-867X

Co-presenter: Robert Carpenter, UMBC

Extended Abstract

As academic technologies mature and are more deeply integrated into higher education, significant ‘data exhaust’ from student and faculty use of these applications provides a rich set of behavioral data that was not previously available.  Over the past decade, data science techniques have been applied to this data and have generated surprising insights. What are some of the most promising results that we’ve seen from this work? What ethical implications are created for institutions, faculty, and practitioners involved in this work?

In this presentation, we will discuss the state of the field from the perspective of a data science leader directing this work and an academic technology leader planning and implementing this work on his campus.  We will provide a brief overview of the field then discuss several studies and deployments of learning analytics that we have collaborated on and/or led from our respective roles.

The studies that we will discuss include:

a. Stealth Assessment of Social and Emotional Skills using Learning Analytics – we analyzed data from student use of the Learning Management System (LMS) in a large-enrollment undergraduate chemistry course and examined the relationships among social and emotional (SE) skills, as measured by ACT® Tessera®, course features, and course grades. Our goal was to understand how SE skills would impact students’ online behaviors and course outcomes and to explore a principled design approach for feature extraction using individual activities and sequential data mining techniques. Findings suggest a new source of insights that can be used to create accurate and actionable predictions to improve student outcomes. No bias based on demographic background was observed in the predictive models.

b. Learner Facing Analytics: Analysis of Student Perspectives from Australia. Within the literature there has been a focus on institutional and academic views related to learning analytics or in fact, what academics in the field feel would be useful to students. This study sought to directly include student perspectives in the conversation around analytics.  Specifically, the study sought to (a) explore student understandings and concerns in relation to learning analytics; (b) gather student input on the types of learning analytics reports, dashboards and tools that will be most useful in supporting student success; (c) develop a series of principles to guide institutions in the creation of student-facing dashboards; and (d) identify the processes and training required to support students and staff to make sense of the data presented in dashboards and improve student success.