Designing an Interactive Teaching Tool with ABML Knowledge Refinement Loop

Matej Zapušek, Martin Možina, Ivan Bratko, Jože Rugelj, Matej Guid

Argument-based machine learning (ABML) knowledge refinement loop offers a powerful knowledge elicitation tool, suitable for obtaining expert knowledge in difficult domains. In this paper, we first use it to conceptualize a difficult, even ill-defined concept: distinguishing between “basic” and “advanced” programming style in python programming language, and then to teach this concept in an interactive learning session between a student and the computer. We demonstrate that by automatically selecting relevant examples and counter examples to be explained by the student, the ABML knowledge refinement loop provides a valuable interactive teaching tool.

The final publication is available at Springer via