Using intelligent agents for the analysis of students’ interaction and learning

Abstract

Years of marking large numbers of group projects on specifications as part of a software engineering course has suggested that although the problems are ill- formed and hence the solutions various, there are some patterns in the learning process. The way students adhere to or deviate from these patterns, such as semantic rules for diagrams, or templates for the report, are a good guide to the students’ understanding of theirwork.We developed software to enable remote groups towork on the projects. To extend this software we have developed a number of rule-based agents that guide students by analysing their learning approach and interaction patterns.