论文信息 - Comparison of Selection Criteria for Multi-Feature Hierarchical Activity Mining in Open Ended Learning Environments

Comparison of Selection Criteria for Multi-Feature Hierarchical Activity Mining in Open Ended Learning Environments

This paper extends our previous work on a Multi-Feature Hierarchical Sequential PAttern Mining (MFH-SPAM) algorithm for deriving students’ behavior patterns from their activity logs in an Open-Ended Learning Environment(OELE). The new algorithm is computationally efficient, and we compare the results generated by the two algorithms.

Yi Dong | Gautam Biswas | John S. Kinnebrew

[1] Gautam Biswas,et al. Learning Behavior Characterization with Multi-Feature, Hierarchical Activity Sequences , 2015, EDM.

[2] Ron Kohavi,et al. Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[3] Erin Shaw,et al. Animated Pedagogical Agents: An Opportunity to be Grasped? , 2002 .

[4] J. Ross Quinlan,et al. Induction of Decision Trees , 1986, Machine Learning.

[5] Susan M. Land. Cognitive requirements for learning with open-ended learning environments , 2000 .

[6] John S. Kinnebrew,et al. A Contextualized, Differential Sequence Mining Method to Derive Students' Learning Behavior Patterns , 2013, EDM 2013.

[7] Johannes Gehrke,et al. Sequential PAttern mining using a bitmap representation , 2002, KDD.