Personalized Review Improves Students’ Long-Term Knowledge Retention


Investigators Mike Mozer and Hal PashlerOutcome:
A software tool that provides individualized review of course material to middle-school students produces a 16.5% boost in retention of complete course content one month after the term’s end, relative to current educational practice. Individualized review also leads to a 10% improvement over a more generic one-size-fits-all review strategy.

A study by researchers in the Temporal Dynamics of Learning Center demonstrates that integrating adaptive, personalized software into the classroom is practical and yields appreciable improvements in long-term educational outcomes. The software addresses a problem that hasn’t been tackled systematically—the fragility of newly acquired information and the curse of forgetting. The software is complementary to in-class instruction, and it allows educators to do what they do well: Introduce new material, explain new concepts, and encourage students toward achieving initial mastery. The review software aims to ensure the durability of this momentary understanding.

Human memory is imperfect. Periodic review is required for the long-term preservation of knowledge and skills. However, students at every educational level are challenged by an ever-growing amount of material to review and an ongoing imperative to master new material. To address these challenges, researchers developed an adaptive method for personalizing study that combines “big data” techniques for inferring individual differences with a psychological theory of memory. This statistical approach leverages data from a population of students studying a variety of material to infer the dynamic knowledge state of an individual student for specific material. The method was incorporated into a semester-long middle school foreign language course via retrieval-practice software which was used for about 30 minutes per week. The software provided a means of comparing the personalized review strategy with two alternative strategies. This comparison was performed by partitioning the material each student learned into thirds, each scheduled by a different strategy and matched for the number of review trials.

Lindsey, R. V., Shroyer, J. D., Pashler, H., & Mozer, M. C. (2014). Improving student's long-term knowledge retention with personalized review. Psychological Science, 25, 639-647. doi: 10.1177/0956797613504302.