Semi-Automatic assessment of students' graph-based diagrams

Diagrams are increasingly used in many design methods, and are being taught in avariety of contexts in higher education such as database conceptual design orsoftware design in computer science. They are an important part of manyassessments. Currently computer aided assessments are widely used for multiplechoice questions. They lack the ability to assess a student’s knowledge in a morecomprehensive way, which is required for diagram-type student work. The aim ofthis research is to develop a semi-automatic assessment framework, which enablesthe use of computer to support the assessment process of diagrammatic solutions,with the focus of ensuring the consistency of grades and feedback on solutions. Anovel trace model, that captures design traces of student solutions, was developed asa part of the framework and was used to provide the matching criteria for groupingthe solutions. A new marking style, partial marking, was developed to mark thesesolution groups manually. The Case-Based Reasoning method is utilised in theframework to mark some of the groups automatically. A guideline for scenariowriting was proposed to increase the efficiency of automatic marking. A prototypediagram editor, a marking tool and scenario writing environment were implementedfor the proposed framework in order to demonstrate proof of concept. The results ofexperiments show that the framework is feasible to use in the formative assessmentand it provides consistent marking and personalised feedback to the students. Theframework also has the potential to significantly reduce the time and effort requiredby the examiner to mark student diagrams. Although the constructed frameworkwas specifically used for the assessment of database diagrams, the framework isgeneric enough to be used for other types of graph-based diagram.