Sense Florian, Behrens Friederike, Meijer Rob R, van Rijn Hedderik
Department of Experimental Psychology, University of Groningen.
Behavioral and Cognitive Neuroscience, University of Groningen.
Top Cogn Sci. 2016 Jan;8(1):305-21. doi: 10.1111/tops.12183. Epub 2016 Jan 8.
One of the goals of computerized tutoring systems is to optimize the learning of facts. Over a hundred years of declarative memory research have identified two robust effects that can improve such systems: the spacing and the testing effect. By making optimal use of both and adjusting the system to the individual learner using cognitive models based on declarative memory theories, such systems consistently outperform traditional methods (Van Rijn, Van Maanen, & Van Woudenberg, 2009). This adjustment process is driven by a continuously updated estimate of the rate of forgetting for each item and learner on the basis of the learner's accuracy and response time. In this study, we investigated to what extent these estimates of individual rates of forgetting are stable over time and across different materials. We demonstrate that they are stable over time but not across materials. Even though most theories of human declarative memory assume a single underlying rate of forgetting, we show that, in practice, it makes sense to assume different materials are forgotten at different rates. If a computerized, adaptive fact-learning system allowed different rates of forgetting for different materials, it could adapt to individual learners more readily.
计算机化辅导系统的目标之一是优化事实性知识的学习。一百多年来的陈述性记忆研究已经确定了两种可以改善此类系统的强大效应：间隔效应和测试效应。通过充分利用这两种效应，并使用基于陈述性记忆理论的认知模型将系统调整至适合个体学习者的状态，此类系统始终优于传统方法（范·里恩、范·马南和范·伍登伯格，2009年）。这个调整过程是由基于学习者的准确性和反应时间对每个项目和学习者的遗忘率进行持续更新的估计所驱动的。在本研究中，我们调查了这些个体遗忘率估计在不同时间和不同材料上的稳定程度。我们证明它们在时间上是稳定的，但在不同材料之间不稳定。尽管大多数人类陈述性记忆理论都假设存在单一的潜在遗忘率，但我们表明，在实际应用中，假设不同材料以不同速率被遗忘是合理的。如果一个计算机化的自适应事实学习系统允许不同材料有不同的遗忘率，那么它就能更轻松地适应个体学习者。
