Learning Analytics: From Research to Practice: 10000 (Computer-Supported Collaborative Learning)

In education today, technology alone doesn't always lead to immediate success for students or institutions. In order to gauge the efficacy of educational technology, we need ways to measure the efficacy of educational practices in their own right. Through a better understanding of how learning takes place, we may work toward establishing best practices for students, educators, and institutions. These goals can be accomplished with learning analytics.

Learning Analytics: From Research to Practice updates this emerging field with the latest in theories, findings, strategies, and tools from across education and technological disciplines. Guiding readers through preparation, design, and examples of implementation, this pioneering reference clarifies LA methods as not mere data collection but sophisticated, systems-based analysis with practical applicability inside the classroom and in the larger world.

Case studies illustrate applications of LA throughoutacademic settings (e.g., intervention, advisement, technology design), and their resulting impact on pedagogy and learning. The goal is to bring greater efficiency and deeper engagement to individual students, learning communities, and educators, as chapters show diverse uses of learning analytics to:

• Enhance student and faculty performance.
• Improve student understanding of course material.
• Assess and attend to the needs of struggling learners.
• Improve accuracy in grading.
• Allow instructors to assess and develop their own strengths.
• Encourage more efficient use of resources at the institutional level.

Researchers and practitioners in educational technology, IT, and the learning sciences will hail the information in Learning Analytics: From Research to Practice as a springboard to new levels of student, instructor, and institutional success.

Johann Ari Larusson is a Senior Research Scientist in the Center for Digital Data, Analytics and Adaptive Learning at Pearson. He first joined Pearson as a Senior Recommendation Engineer where he led research and development of recommendation engine technologies and adaptivity and analytics for the Alleyoop product. His research and applied work are primarily in the fields of educational technology, learning analytics, computer-mediated collaborative learning (CSCL) and software engineering. Prior to Pearson, he held various R&D positions in the technology industry, academia and banking. Even prior to educational technology, his work centered around transmission, manipulation and analysis of large volumes of (unstructured) data. Johann has authored and co-authored several peer-reviewed and award-winning publications, was a founding member and chair of the First North East Regional Learning Analytics Symposium, and has served as a reviewer for a number of journals and conferences. He holds a Ph.D. in Computer Science from Brandeis University.

Brandon White is a doctoral candidate in English at the University of California, Berkeley, where his theoretical interests in pedagogical history intersect with inquiries in applied educational technology. His work and research in learning analytics primarily concerns language recasting as deployed in student writing, and as taken up by educational theory, linguistics, and psychology. He is particularly invested in developing methods for identifying, isolating, and weighing markers for students’ success based on their written content. Before coming to Berkeley, he was a Teaching and Learning Fellow at Brandeis University, where he also earned his Master’s degree in Cultural Production, and continued to work as a consultant in educational technology for Research and Instruction Services. He is the author of a number of peer-reviewed publications and has served on several advisory committees for teaching and learning in higher education.