An Improved Method for Label Matching in E-Assessment of Diagrams
Taylor and Francis
MetadataShow full item record
A challenging problem for e-assessment is automatic marking of diagrams. There are a number of difficulties not least that much of the meaning of a diagram resides in the labels and hence label matching is an important process in the e-assessment of diagrams. Previous research has shown that the labels used by the students in the diagrams can be diverse and imprecise which makes this problematic. In this paper we propose and evaluate a new method for label matching to support e-assessment of diagrams and address problems of synonyms, spelling errors and differing levels of decomposition. We have implemented the syntactic part of our method and evaluated it using 160 undergraduate assessments based upon a UML design task. We have found that our method performs better than the other syntax matching algorithms. This framework has significant implications for the ease in which we may develop future e-assessment systems. The results from this pilot study have been encouraging and motivate us to implement the semantic similarity part of our method and conduct further evaluations.
Innovation in Teaching and Learning in Information and Computer Sciences;
Jayal, A. and Shepperd, M. (2009) 'An improved method for label matching in e-assessment of diagrams', Innovation in Teaching and Learning in Information and Computer Sciences, 8(1), pp.3-16. DOI: 10.11120/ital.2009.08010003.
Article published in Innovation in Teaching and Learning in Information and Computer Sciences online on 15 December 2015, available open access at: https://doi.org/10.11120/ital.2009.08010003.
Showing items related by title, author, subject and abstract.
Jayal, Ambikesh; Shepperd, Martin (Association for Computing Machinery (ACM), 2009-01)In this article we explore a problematic aspect of automated assessment of diagrams. Diagrams have partial and sometimes inconsistent semantics. Typically much of the meaning of a diagram resides in the labels; however, ...
Students Understanding of Alcohol Nutrition Labelling and the Subsequent Impact on Attitudes and Alcohol Consumption Brown, David (Cardiff Metropolitan University, 2017-06-01)Background Although obligated to inform consumers of the Alcohol by volume (ABV%) and Unit quantities of alcoholic products, producers rarely display Calorie (Kcal) information on their package labels. Students are ...
The chemical analysis of food constituents to determine the relationship between food content and its labelling with a particular focus on protein content Sparrow, James (University of Wales Institute Cardiff, 2012)Introduction: The relationship between diet and the development of various chronic diseases is becoming ever more apparent. Food labelling helps to inform the consumer as to the exact content of the food products they are ...