Authors:
Zohra Ben Said
1
;
Fabrice Guillet
1
;
Paul Richard
2
;
Julien Blanchard
1
and
Fabien Picarougne
1
Affiliations:
1
University of Nantes, France
;
2
University of Angers, France
Keyword(s):
Visual Data Mining, Visualization, Knowledge Discovery in Database, Association Rules.
Related
Ontology
Subjects/Areas/Topics:
Abstract Data Visualization
;
Computer Vision, Visualization and Computer Graphics
;
Databases and Visualization, Visual Data Mining
;
Visual Data Analysis and Knowledge Discovery
Abstract:
In order to discover knowledge from large amount of results generated by the association rules extraction algorithms, visual representations of association rules can be very beneficial to the user. Those representations support the user in finding and validating interesting knowledge. All techniques proposed for association rule visualization have been developed to represent association rule as a hole without paying attention to the relations between attributes and the contribution of each one. In this article, we propose a new visualization metaphor for association rules. This new metaphor represents attributes which make up the antecedent and the consequent, the contribution of each one to the rule, and the correlations between each pair of antecedent and consequent.