Smart Learning Environments: Potential and Pitfalls

Abstract

The history of educational technology in the last 50 years contains few instances of dramatic improvements in learning based on the adoption of a particular technology. An example involving a smart learning technology occurred in the 1990s with the development of intelligent tutoring systems (ITSs). The success of ITSs was limited to constrained and straightforward learning tasks (e.g., learning how to write a LISP function; doing multi-column addition), and improvements that were observed tended to be more limited than promised (e.g., one standard deviation improvement at best rather than the promised standard deviation improvement). Still, there was some progress in terms of how to conceptualize personalized instruction. A seldom documented limitation was the notion of only viewing learning from the perspective of content and cognition (i.e., in terms of memory limitations, prior knowledge, bug libraries, learning hierarchies, and hierarchical sequences). Little attention was paid to education conceived more broadly than simply developing specific cognitive skills with highly constrained problems. Recent technologies offer the potential to create dynamic, multi-dimensional models of individual learners, and to track large data sets of learning activities, resources, interventions, and outcomes over a great many learners. Using those data to personalize learning for a particular learner as they develop knowledge, competence, and understanding in a specific domain of inquiry is now a real possibility. While the potential to make significant progress is clearly possible, the reality is less promising. There are many as yet unmet challenges and pitfalls some of which are mentioned in this paper. A persistent worry is that educational technologists and computer scientists will again promise too much, too soon, at too little cost, and with too little effort and attention to the realities in schools and universities.