Mining the Web to Suggest Concepts during Concept Mapping: Preliminary Results

Abstract

Resumo: The most challenging aspect of constructing a concept map is not coming up with the list of concepts to include, but linking the concepts into meaningful propositions creating a coherent structure that reflects the learner’s understanding of a domain. We present an algorithm that, during the process of concept mapping, takes the partially constructed map as input to mine the web, and presents to the user a list of suggested concepts that are relevant to the map under construction. Testing a preliminary implementation of the algorithm with a set of users during a concept-mapping workshop seems to validate its viability. Depending on the size of the suggestion list, the algorithm presented on average between 47% and 69% of the concepts in the final maps before the users added them to the map, showing that the algorithm is able to retrieve concepts relevant to the concept mapping effort. Abstract: The most challenging aspect of constructing a concept map is not coming up with the list of concepts to include, but linking the concepts into meaningful propositions creating a coherent structure that reflects the learner’s understanding of a domain. We present an algorithm that, during the process of concept mapping, takes the partially constructed map as input to mine the web, and presents to the user a list of suggested concepts that are relevant to the map under construction. Testing a preliminary implementation of the algorithm with a set of users during a concept-mapping workshop seems to validate its viability. Depending on the size of the suggestion list, the algorithm presented on average between 47% and 69% of the concepts in the final maps before the users added them to the map, showing that the algorithm is able to retrieve concepts relevant to the concept mapping effort.