Rapid Dynamic Assessment of Expertise to Improve the Efficiency of Adaptive E-learning

In this article we suggest a method of evaluating learner expertise based on assessment of the content of working memory and the extent to which cognitive load has been reduced by knowledge retrieved from long-term memory. The method was tested in an experiment with an elementary algebra tutor using a yoked control design. In the learner-adapted experimental group, instruction was dynamically tailored to changing levels of expertise using rapid tests of knowledge combined with measures of cognitive load. In the nonadapted control group, each learner was exposed to exactly the same instructional procedures as those experienced by the learner’s yoked participant. The experimental group demonstrated higher knowledge and cognitive efficiency gains than the control group. Processing limitations of human working memory are known to be a major factor influencing the effectiveness of instructional presentations. A limited working memory capacity could easily be overloaded if more than a few chunks of information are processed at the same time (e.g., Baddeley, 1986; Miller, 1956). Organized, domain-specific, long-term memory knowledge structures (or schemas) allow people to overcome the limitations of working memory by “chunking” many elements of information into a single, higher-level element (see Chi, Glaser, & Rees, 1982; Larkin, McDermott, Simon, & Simon, 1980). By treating many elements of information as a single element in working memory, long-term memory schematic knowledge structures may reduce working memory load. Another way to reduce working memory processing limitations is to practice the skills provided by schemas until they can operate under automatic rather than controlled processing (Kotovsky, Hayes, & Simon, 1985; Shiffrin & Schneider, 1977). From a cognitive load perspective, the major role of learning in cognitive functioning is acquisition and automation of schematic knowledge structures in long-term memory. As our previous research on the expertise reversal effect indicated (see Kalyuga, Ayres, Chandler, & Sweller, 2003 for an overview), the effectiveness of learning from different instructional formats and procedures may significantly alter with the development of learner expertise in a domain, because of cognitive load factors. As learners acquire more knowledge in a domain, their prevailing cognitive activities change. Construction of new schemas is the novice’s dominant cognitive activity that requires appropriate instructional support. In contrast, experts tend to