Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.607158
Title: The automatic assessment of multiple artefacts : an investigation into design diagrams and their implementations
Author: Hayes, Alan Michael
ISNI:       0000 0004 5362 2807
Awarding Body: Open University
Current Institution: Open University
Date of Award: 2014
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
As the Higher Education sector has moved towards student-centred learning so too has the growth in electronic support for learning. E-assessment has been a part of this growth as increasingly assessment and its feedback is seen as an integral part of the students’ learning process. Mature e-assessment systems exist, particularly where answers to questions are restricted to a prescribed list of alternatives. However, for free response artefacts, where there is a limited restriction placed on answers to questions, automated assessment systems are embryonic. This dissertation presents an investigation into the automated assessment of free response artefacts. Design diagrams and their accompanying source code implementations are examples of free response artefacts. A case study is developed that investigates how to automatically generate formative feedback for a design diagram by utilizing its accompanying implementation. The dissertation presents a two-staged solution, initially analysing the design diagram in isolation before comparing it with the implementation. A framework for this approach has been developed and tested using a tool applied to coursework submitted by undergraduate computer science students. The tool was evaluated by comparing the formative feedback comments generated by the tool with those produced by a team of computer science educators. Evaluation was undertaken via two Likert questionnaires, one completed by students and one completed by a team of computer scientists. The results presented are favourable, with the majority of comments produced by the tool being seen to be as least as good as those generated by the computer science educators.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.607158  DOI: Not available
Share: