Bodong Chen

Crisscross Landscapes

Notes: Identifying Learning Behaviors by Contextualizing Differential Sequence Mining with Action Features and Performance Evolution



Kinnebrew, J., & Biswas, G. (2012). Identifying Learning Behaviors by Contextualizing Differential Sequence Mining with Action Features and Performance Evolution. In the 5th International Conference on Educational Data Mining (pp. 57–64). Retrieved from

Citekey: @Kinnebrew2012


The core algorithm employs sequence mining techniques to identify differentially frequent patterns between two predefined groups. (p. 1)

In developing a computer-based learning environment (CBLE) called Betty’s Brain, we have adopted a self-regulated learning (SRL) framework to help students develop learning strategies. (p. 1)

To identify important activity patterns in a comparison between two sets of action sequences, our methodology employs a novel combination of sequence mining techniques. (p. 3)

Sequential pattern mining [2] methods find the most frequent action patterns across a set of action sequences, while episode mining [11] discovers the most frequently used action patterns within a given sequence. (p. 3)

The details of our differential sequence mining algorithm are presented in [8], but we briefly outline the main steps of the algorithm. First, a sequential pattern mining algorithm (SPAMc [6]) identifies the patterns that meet a minimum s-support constraint within each group, employing a maximum gap constraint to account for noise, which is interpreted as a small number of irrelevant actions that may be interspersed in a pattern. In this paper, we employ a gap constraint of 1, i.e., we allow at most one irrelevant action between each consecutive action in a pattern. To compare the identified s-frequent patterns across groups, we calculate the mean i-support of every pattern for each group. In order to identify patterns whose usage more clearly differ between the two groups, we also filter the patterns based on the p value of a t-test comparing pattern i-support between the groups. (p. 4)

Overall, high-performing students differentially employed reading behaviors that indicated a more careful and systematic strategy of reading. Their activity patterns more frequently involved re-reading pages from the resources, such as employing full-length re-reads of the resources before adding a link. Further, the reading activity patterns distinguishing high-performers from low-performers usually involved reading pages that were relevant to recent actions, suggesting a more systematic reading behavior overall. Productive periods were particularly distinguished in high performers by a larger number of full-length, relevant re-read actions. (p. 7)

Performance was also linked to monitoring behaviors that incorporated re-reading of the resource material. In particular, high-performers were more likely to employ various types of reading actions both before and after assessments of progress/correctness using the quiz. Low performers, on the other hand, had a differential tendency to use irrelevant, extended re-reads of pages in the resources during productive periods. (p. 7)