Improving Teaching and Learning through Automated Short-Answer Marking

Automated short-answer marking cannot “guarantee” 100 percent agreement between the marks generated by a software system and marks produced separately by a human. This problem has prevented automated marking systems from being used in high-stake short-answer marking. This paper describes how an automated short-answer marking system, called IndusMarker, can be effectively used to improve teaching and learning in an Object-Oriented Programming course taught at a university. The system is designed for factual answers where there is a clear criterion for answers being right or wrong. The system is based on structure matching, i.e., matching a prespecified structure, developed via a purpose-built structure editor, with the content of the student's answer text.