Adapting to When Students Game an Intelligent Tutoring System

Abstract

It has been found in recent years that many students who use intelligent tutoring systems game the system, attempting to succeed in the educational environment by exploiting properties of the system rather than by learning the material and trying to use that knowledge to answer correctly. In this paper, we introduce a system which gives a gaming student supplementary exercises focused on exactly the material the student bypassed by gaming, and which also expresses negative emotion to gaming students through an animated agent. Students using this system engage in less gaming, and students who receive many supplemental exercises have considerably better learning than is associated with gaming in the control condition or prior studies.

Carelessness and Affect in an Intelligent Tutoring System for Mathematics

“…Scooter was designed to reduce the incentive to game the system and to help students learn the material that they were avoiding by gaming, while affecting non-gaming students as minimally as possible. Previous research in the United States found that Scooter reduced gaming, while increasing learning for gaming students (Baker et al 2006); however, these patterns were not statistically significant in the Philippines . The remaining 62 participants (Control or NoScooter group) used a version of the Scatterplot Tutor without the pedagogical agent.…”

“…Data were gathered from 126 public high school students in Quezon City, Philippines (labeled PH below), who used a Cognitive Tutor unit on scatterplot generation and interpretation (Baker et al 2006) for 80 min, inside the school's computer center, after school. The students were between 12 and 14 years old.…”

“…We also established the detectors' generalizability to new data from new student populations by applying our detectors trained on data from students in the Philippines to Scatterplot log data from a school in the USA. These interaction logs from the USA (described in greater detail in Baker et al 2006) were gathered from 6th-8th grade students, in the suburbs of a medium-sized city in the Northeastern USA. Fifty-two students used the Scooter version of the tutor, and 65 students used the NoScooter version.…”

New Potentials for Data‐Driven Intelligent Tutoring System Development and Optimization

“…For example, an automated agent that addresses gaming behavior has been developed, based on an automated detector of gaming (Baker et al 2006). This agent gave students supplementary exercises on material bypassed through gaming and displayed displeasure when the student games.…”

“…This agent gave students supplementary exercises on material bypassed through gaming and displayed displeasure when the student games. In a classroom study in the USA, this agent reduced gaming by half and improved gaming students' learning relative to the control condition (Baker et al 2006 (2009) found that supportive messages, given when negative affect occurred, improved affect for struggling students, while shake-up messages improved affect for more successful students.…”