Please use this identifier to cite or link to this item:
Title: The problem of labels in e-assessment of diagrams
Authors: Jayal, A
Shepperd, M J
Keywords: e-Learning;e-Assessment;empirical research;diagrams;UML;text processing
Issue Date: 2008
Citation: ACM Journal on Educational Resources in Computing (JERIC), 8(4).
Abstract: In this short paper we explore a problematic aspect of automated assessment of diagrams. Diagrams have partial and sometimes inconsistent semantics. Typically much of the meaning of diagram resides in the labels, however, the choice of labeling is largely unrestricted. This means a correct solution may utilise differing yet semantically equivalent labels to the specimen solution. With human marking this problem can be easily overcome. Unfortunately with e-assessment this is challenging. We empirically explore the scale of the problem of synonyms by analysing 160 student solutions to a UML task. From this we find that cumulative growth of synonyms only shows a limited tendency to reduce at the margin. This finding has significant implications for the ease in which we may develop future e-assessment systems of diagrams, in that the need for better algorithms for assessing label semantic similarity becomes inescapable.
Appears in Collections:Computer Science
Dept of Computer Science Research Papers
Software Engineering (B-SERC)

Files in This Item:
File Description SizeFormat 
JERIC_v20.pdf257.85 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.