Auto-assessor: Computerized assessment system for marking student's short-answers automatically

Laurie Cutrone, Maiga Chang, Kinshuk

Research output: Chapter in Book/Report/Conference proceedingPublished Conference contributionpeer-review

27 Citations (Scopus)

Abstract

A number of Learning Management Systems (LMSs) exist on the market today. A subset of a LMS is the component in which student assessment is managed. In some forms of assessment, such as short-answer questions, the LMS is incapable of evaluating the students' responses and therefore human intervention is necessary. This study leverages the research conducted in recent Natural Language Processing studies to provide a fair, timely and accurate assessment of student short-answers based on the semantic meaning of those answers. A component-based system utilizing a Text Pre-Processing phase and a Word/Synonym Matching phase has been developed to automate the marking process. An evaluation plan is also made to verify the possibility of applying such computerized assessment system in practical situations as well as to reveal areas in which the system could be improved later.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Technology for Education, T4E 2011
Pages81-88
Number of pages8
DOIs
Publication statusPublished - 2011
Event3rd International Conference on Technology for Education, T4E 2011 - Chennai, Tamil Nadu, India
Duration: 14 Jul. 201116 Jul. 2011

Publication series

NameProceedings - IEEE International Conference on Technology for Education, T4E 2011

Conference

Conference3rd International Conference on Technology for Education, T4E 2011
Country/TerritoryIndia
CityChennai, Tamil Nadu
Period14/07/1116/07/11

Keywords

  • WordNet
  • computerized grading
  • natural language processing
  • semantic meaning
  • short-answer question

Fingerprint

Dive into the research topics of 'Auto-assessor: Computerized assessment system for marking student's short-answers automatically'. Together they form a unique fingerprint.

Cite this