Learning analytics in large college courses : facilitating retention and transfer through targeted retrieval practice
MetadataShow full item record
Spaced retrieval practice is known to benefit both long-term retention and transfer of learning, two important goals of education. However, most classes are not designed in a way that facilitates frequent quizzing or revisiting previously covered topics; this is particularly true in higher education, where a small number of exams typically account for the bulk of a student’s grade. Recently, a large undergraduate course at the University of Texas has implemented a new class structure that replaces high-stakes tests with daily quizzes administered during class via computer; furthermore, quiz items previously answered incorrectly can appear at random on future quizzes. Together, these innovations are an excellent first step toward bringing spaced retrieval practice into the college classroom. However, I propose that technology can be further leveraged in classes such as these to more optimally choose repeated items. Given graded student quiz data from one semester of this course, I use Multidimensional Item Response Theory (MIRT) and Sparse Factor Analysis (SPARFA) to jointly estimate concepts underlying the items and each students’ mastery of these concepts. After comparing these factor-analytic methods, I also explore free-response and student chat data using basic natural language processing. It is concluded that techniques from learning analytics can help realize the full potential of spaced retrieval practice in the classroom by optimizing the selection of repeated items so as to target remediation. Furthermore, such techniques can be used to introduce variability into retrieval practice, encouraging a deeper understanding of the content which is more likely to transfer to novel problems.