Abstract. One of the main problems with Adaptive Educational Hypermedia Systems (AEHS) is that is very difficult to test whether adaptation decisions are beneficial for all the students or some of them would benefit from a different adaptation. Data mining techniques can provide support to overcome, to a certain extent, this problem. This paper proposes the use of these techniques for detecting potential problems of adaptation in AEH systems. The proposed method searches for symptoms of these problems (called anomalies) through log analysis and tries to interpret the findings. Currently, a decision tree technique is being used for the task. 1

We attempt to automatically detect student frustration, at a coarsegrained level, using measures distilled from student behavior within a learning environment for introductory programming. We find that each student’s average level of frustration across five lab exercises can be detected based on the number of pairs of consecutive compilations with the same edit location, the number of pairs of consecutive compilations with the same error, the average time between compilations and the total number of errors. Attempts to detect frustration at a finer grain-size, identifying individual students ’ fluctuations in frustration between labs, were less successful. These results indicate that it is possible to detect frustration at a coarse-grained level, solely from coarse-grained data about students ’ behavior within a learning environment.