Posted: February 2, 2015
The adoption of Affective Computing principles and data analytics are not limited to wearable technology and self-quantification. These principles are now emerging in the teaching and learning space. The New Media Consortium (2014) discusses the growth of data-driven learning and assessment, and how it will impact higher education in the next three to five years in its annual report on Higher Education.
In the early 1990s, customer relation management systems began to emerge, as companies started gathering information about customer preferences and customer behavior. The same analytics science user by companies to optimize profits for consumer product development and marketing is being adaptive to the science of learning analytics. Online learning environments in particular generate a tremendous amount of learning related data; by applying data mining techniques and statistical analysis to this data, it is possible to derive instructional decisions to optimize learning at many different target points, from subject areas down to individual students in a specific course.
Adaptive Learning Software is becoming quite sophisticated. In 2013 Pearson integrative adaptive learning into online courses, detecting patterns of student success and failure and applied customize tutoring services (New Media Consortium). Other experimental studies are even more sophisticated, moving beyond course success criteria. MIT’s Media Lab has conducted a number of studies in which student interest (i.e. affect) is measured using a variety of physiological indicate such as facial expressions, heart rate, and posture (Mota & Picard, 2003). The combination of real time course performance data and physiological monitoring to determine student affect and interest has the potential to bring truly intelligent tutoring systems to computer-based learning.
One of the challenges faced by educational institutions is how to protect student privacy while using data to personalize the student experience. Universities are already beginning to formalize polices on how student learning data is gathered and used to make instructional decisions. Even Ivy League institutions like Harvard still have room for growth in this space. In a 2014 article published in the Boston Globe, it was released that Harvard ran a serious of clandestine experiments in which it secretly photographed 2,000+ students in lecture hall earlier this year without student consent. This led Harvard to implement new privacy and data gathering policies (Rocheleau, 2014).
New Media Consortium. (n.d.). NMC horizon project. Retrieved from http://www.nmc.org/horizon-project.
New Media Consortium. (n.d.). The NMC Horizon Report: 2014 Higher Education Edition Wiki. Retrieved January 30, 2015, from http://horizon.wiki.nmc.org.
New Media Consortium. (n.d.). The NMC Horizon Report: 2014 Higher Education Edition. Retrieved January 30, 2015, from http://cdn.nmc.org/media/2014-nmc-horizon-report-he-EN-SC.pdf.
Mota, S., & Picard, R. W. (2003, June). Automated posture analysis for detecting learner’s interest level. In Computer Vision and Pattern Recognition Workshop, 2003. CVPRW’03. Conference on (Vol. 5, pp. 49-49). IEEE.
Rocheleau, M. (2014, November 5). Harvard secretly photographed students to study attendance. Boston Globe. Retrieved January 30, 2015, from http://www.bostonglobe.com/metro/2014/11/05/harvard-secretly-photographed-students-study-class-attendance-raising-privacy-concerns/hC8TBdGdZmQehg0lAhnnJN/story.html
Sidney, K. D., Craig, S. D., Gholson, B., Franklin, S., Picard, R., & Graesser, A. C. (2005). Integrating affect sensors in an intelligent tutoring system. In Affective Interactions: The Computer in the Affective Loop Workshop at (pp. 7-13).