Squeezing Out Gaming Behavior in a Dialog-Based ITS

Peter Hastings, Elizabeth Arnott-Hill, David Allbritton

Research Methods Tutor (RMT) is a dialog-based intelligent tutoring system which has been used by students in Research Methods in Psychology classes since 2003. Students interact with RMT to reinforce what they learn in class in five different topics. In this paper, we evaluate a different population of students and replicate our prior research: despite the relatively small amount of exposure during the term to RMT compared to other course-related activities, students learn significantly more on topics covered with RMT [1]. However, we did not find the same advantage for the dialog-based tutoring mode of RMT over the CAI mode. When transcript analyses indicated that a small but significant number of students were gaming the system by entering empty or nonsense responses, we modified the tutor to require reasonable attempts. This did lead some students to reform their gaming ways. In other cases, however, it resulted in disengagement from tutoring at least temporarily because reasonable answers were not recognized.

The final publication is available at Springer via https://doi.org/10.1007/978-3-642-13388-6_25.