Early Warning Systems and Targeted Interventions for Student Success in Online Courses

Online learning has increasingly been viewed as a possible way to remove barriers associated with traditional face-to-face teaching, such as overcrowded classrooms and shortage of certified teachers. While online learning has been recognized as a possible approach to deliver more desirable learning outcomes, close to half of online students drop out as a result of student-related, course-related, and out-of-school-related factors (e.g., poor self-regulation; ineffective teacher-student, student-student, and platform-student interactions; low household income). Many educators have expressed concern over students who unexpectedly begin to struggle and appear to fall off track without apparent reason. A well-implemented early warning system, therefore, can help educators identify students at risk of dropping out and assign and monitor interventions to keep them on track for graduation. Despite the popularity of early warning systems, research on their design and implementation is sparse.

Early Warning Systems and Targeted Interventions for Student Success in Online Courses is a cutting-edge research publication that examines current theoretical frameworks, research projects, and empirical studies related to the design, implementation, and evaluation of early warning systems and targeted interventions and discusses their implications for policy and practice. Moreover, this book will review common challenges of early warning systems and dashboard design and will explore design principles and data visualization tools to make data more understandable and, therefore, more actionable. Highlighting a range of topics such as curriculum design, game-based learning, and learning support, it is ideal for academicians, policymakers, administrators, researchers, education professionals, instructional designers, data analysts, and students.

Danny Glick is a Research Affiliate at the University of California, Irvine’s Online Learning Research Center where he explores ways to improve student persistence and performance in online courses using early warning systems and light-touch interventions. He is a former visiting scholar at the University of California, Irvine’s School of Education where he investigated the effects of blended learning on the achievement of low-income students. Dr. Glick is also the Director of Pedagogical Implementation at Edusuft, a subsidiary of ETS, where he leads a team of EdTech implementation specialists. For the past 20 years, he has helped ministries of education and higher education institutions in 35 countries to shift from traditional instruction to online learning. Dr. Glick holds a PhD in Learning Technologies and a Master’s degree in Curriculum & Instruction, and has presented and published on topics including early warning systems, targeted interventions, student persistence, and learning design.

Anat Cohen (PhD) is a senior academic staff at Tel Aviv University's School of Education, where she heads the Learning and Technology program in the Department of Education in Mathematics, Science and Technology. She is a deputy chair holder of technology and education affairs in the UNESCO Chair in Technology, Internationalization and Education; a research coordinator of Web-Supported Academic Instruction at Tel-Aviv University (Virtual TAU); and the PI of a research project funded by the Education Ministry's chief scientist: Integrating Mathematical Applets in the Teaching Sequence. Dr. Cohen has vast research and teaching experience in the field of learning and cyber technologies. For the past 20 years she has been engaged in developing online learning materials, training academic staff and characterizing how to fit learning-management features to the university’s needs. Her research activities focus on areas such as learning analytics and educational data-mining, social networks and privacy perception, ICT implementation in higher education, cost-effectiveness of online learning, open educational resources (learning object repositories & MOOCs) and mobile-assisted learning.

Chi Chang is a tenure-track assistant professor in the Office of Medical Education Research and Development and the Department of Epidemiology and Biostatistics in the School of Human Medicine at Michigan State University. She earned her PhD in Measurement and Quantitative Methods. She holds master’s degrees in Biostatistics and Educational Administration and Policy, and has a background in teacher education, educational psychology, and counselling. Her research interests center on classification methodologies and cognitive diagnostic assessments. She evaluates the quality of parameter estimation among statistical methods under various conditions using simulation studies. Her psychometric research focuses on diagnosing students’ cognitive skills and exploring methodologies to identify students’ learning patterns, progress performance, clinical knowledge, and clinical skills. Chang’s interests include multilevel modeling, finite mixture modeling, measurement invariance, and meta-analysis. Currently, her research is focused on applying neural network algorithms to optimize classification accuracy. She has projects applying pattern recognition and recurrent neural networks to multi-site program evaluation and medical education.