Affect, Carelessness, Cognitive Tutors, Educational data mining
We investigate the relationship between students’ affect and their frequency of careless errors while using an Intelligent Tutoring System for middle school mathematics. A student is said to have committed a careless error when the student’s answer is wrong despite knowing the skill required to provide the correct answer. We operationalize the probability that an error is careless through the use of an automated detector, developed using educational data mining, which infers the probability that an error involves carelessness rather than not knowing the relevant skill. This detector is then applied to log data produced by high-school students in the Philippines using a Cognitive Tutor for scatterplots. We study the relationship between carelessness and affect, triangulating between the detector of carelessness and field observations of affect. Surprisingly, we find that carelessness is common among students who frequently experience engaged concentration. This finding implies that a highly engaged student may paradoxically become overconfident or impulsive, leading to more careless errors. In contrast, students displaying confusion or boredom make fewer careless errors. Further analysis over time suggests that confused and bored students have lower learning overall. Thus, their mistakes appear to stem from a genuine lack of knowledge rather than carelessness.