Abstract
Purpose - This study proposes a blackboard approach using multistrategy machine learning student modeling techniques to learn the properties of students’ inconsistent behaviors during their learning process.Design/methodology/approach - These multistrategy machine learning student modeling techniques include inductive reasoning (similarity-based learning), deductive reasoning (explanation-based learning), and analogical reasoning (case-based reasoning).Findings - According to the properties of students’ inconsistent behaviors, the ITS (intelligent tutoring system) may then adopt appropriate methods, such as intensifying teaching and practing, to prevent their inconsistent behaviors from reoccurring.Originality/value - This research sets the learning object on a single student. After the inferences are accumulated from a group of students, what kinds of students tend to have inconsistent behaviors or under what conditions the behaviors happened for most students can be learned.
Purpose - This study proposes a blackboard approach using multistrategy machine learning student modeling techniques to learn the properties of students’ inconsistent behaviors during their learning process.Design/methodology/approach - These multistrategy machine learning student modeling techniques include inductive reasoning (similarity-based learning), deductive reasoning (explanation-based learning), and analogical reasoning (case-based reasoning).Findings - According to the properties of students’ inconsistent behaviors, the ITS (intelligent tutoring system) may then adopt appropriate methods, such as intensifying teaching and practing, to prevent their inconsistent behaviors from reoccurring.Originality/value - This research sets the learning object on a single student. After the inferences are accumulated from a group of students, what kinds of students tend to have inconsistent behaviors or under what conditions the behaviors happened for most students can be learned.