Cmap
A New Approach to Meaningful Learning Assessment using Concept Maps: Ontologies and Genetic Algorithms

Da Rocha, Francisco E. Lopes and Da Costa , Júlio V. and Favero, Eloi L. (2004) A New Approach to Meaningful Learning Assessment using Concept Maps: Ontologies and Genetic Algorithms. In: Concept Maps: Theory, Methodology, Technology. Proc. of the First Int. Conference on Concept Mapping. Universidad Pública de Navarra, Pamplona, Spain, pp. 175-182. ISBN 84-9769-064-8

[img]
Preview
PDF - Published Version
Download (104kB) | Preview
Official URL: http://cmc.ihmc.us

Abstract

In this article we discuss the use of concept maps (CMs) in learning assessment. As an alternative to the comparison of the learner’s CM with the teacher’s CM, in order to certify what is right or wrong or to attribute a grade, we present a new approach to assess CMs: we consider learning assessment as an adaptive and evolutionary problem and we show how to use ontologies and machine learning, through genetic algorithms (GAs), to assess CMs. The ontologies we use store knowledge, in the form of concepts and propositions, and functions to measure the semantic distance between CMs. The GA, using the ontology, generates the search space (collections of CMs) used to show learners the alternatives to their possible faults when learning concepts and propositions. The complete assessment of a CM includes the analysis of its hierarchical structure, the recognition of learning types, and the analysis of semantic similarity with the CMs of the search space. We also show the actions executed by the GA to construct the CMs of the search space and the concepts present in the ontology and ignored by the learner.

Item Type: Book Section
Uncontrolled Keywords: Paper, CMC2004
Subjects: L Education > L Education (General)
Q Science > QA Mathematics > QA76 Computer software
Divisions: UNSPECIFIED
Depositing User: Mr. Ernest Prats
Date Deposited: 15 Aug 2012 08:59
Last Modified: 10 Oct 2012 18:38
URI: http://eprint.ihmc.us/id/eprint/63

Actions (login required)

View Item View Item