Using Knowledge Discovery Techniques to Support Tutoring in an Open World Intelligent Game-Based Learning Environment

This study covers the attempt to incorporate a proposed knowledge discovery framework in an open world Intelligent Game-Based Learning Environment (IGBLE) to further improve the use's experience. Four phases were done in order to come up with the framework: (1) sequential pattern mining using PrefixSpan of user's action log, (2) association rule mining of the generated patterns, (3) extracting generic rules using Informative Generic Base (IGB) algorithm and (4) integrating it to the IGBLE. The framework produced a learned Procedural Task Knowledge (PTK) that served as a mechanism to support tutoring for the selected game. This implies that the new IGBLE incorporated with the framework provided significantly better guidance to the players through recommending good and easy-to-follow sequences of actions.

[1]  Antonija Mitrovic,et al.  A Comparative Analysis of Cognitive Tutoring and Constraint-Based Modeling , 2003, User Modeling.

[2]  Jianyong Wang,et al.  Mining sequential patterns by pattern-growth: the PrefixSpan approach , 2004, IEEE Transactions on Knowledge and Data Engineering.

[3]  Jonathan P. Rowe,et al.  Player Goal Recognition in Open-World Digital Games with Long Short-Term Memory Networks , 2016, IJCAI.

[4]  Engelbert Mephu Nguifo,et al.  A new Informative Generic Base of Association Rules , 2005, CLA.

[5]  Stephen B. Blessing,et al.  A Programming by Demonstration Authoring Tool for Model-Tracing Tutors , 2003 .

[6]  Ramakrishnan Srikant,et al.  Mining sequential patterns , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[7]  Jonathan P. Rowe,et al.  Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks , 2014 .

[8]  Vincent Aleven,et al.  The Cognitive Tutor Authoring Tools (CTAT): Preliminary Evaluation of Efficiency Gains , 2006, Intelligent Tutoring Systems.

[9]  Qiming Chen,et al.  PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth , 2001, Proceedings 17th International Conference on Data Engineering.

[10]  Tanja Mitrovic,et al.  Constraint-based tutors: a success story , 2001, AIED.

[11]  Sebastian Arnold,et al.  Adaptive Behavior with User Modeling and Storyboarding in Serious Games , 2013, 2013 International Conference on Signal-Image Technology & Internet-Based Systems.

[12]  Neil T. Heffernan,et al.  Applying Machine Learning Techniques to Rule Generation in Intelligent Tutoring Systems , 2004, Intelligent Tutoring Systems.