While there is evidence that user-adaptive support can greatly enhance the
effectiveness of educational systems, designing such support for exploratory
learning environments (e.g., simulations) is still challenging due to the
open-ended nature of their interaction. In particular, there is little a priori
knowledge of which student's behaviors can be detrimental to learning in such
environments. To address this problem, we focus on a data-driven user-modeling
framework that uses logged interaction data to learn which behavioral or
activity patterns should trigger help during interaction with a specific
learning environment. This framework has been successfully used to provide
adaptive support in interactive learning simulations. Here we present a novel
application of this framework we are working on, namely to Massive Open Online
Courses (MOOCs), a form of exploratory environment that could greatly benefit
from adaptive support due to the large diversity of their users, but typically
lack of such adaptation. We describe an experiment aimed at investigating the
value of our framework to identify student's behaviors that can justify
adapting to, and report some preliminary results.

本文介绍了使用数据驱动的用户建模框架来设计用户自适应支持，在学习模拟器和 MOOCs 中提供自适应支持的实验，旨在研究该框架的应用价值。