Affiliations: Institute of Informatics, Silesian University of Technology, Gliwice, Poland
Note: [] Corresponding author. Urszula Stańczyk, Institute of Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland. E-mail: [email protected]
Abstract: Knowledge discovered from data can be represented in a form of decision rules, consisting of required conditions and decisions to which they lead. The quality of rules is usually considered in terms of some quantitative measures such as confidence, support or length. Depending on all these parameters the constructed classifiers can greatly vary in the predictive accuracy and the size of their structure. Both these elements depend strongly on the choice of characteristic features, which can be found by some independent feature selection procedure, but also by applying a wrapper model. In the wrapper model the classifier and its parameters are used to evaluate the importance of attributes. In the paper there are proposed measures of attribute relevance based on rule lengths. The usefulness of the described methodology is shown for rule-based classifiers, obtained through Dominance-Based Rough Set Approach, and a connectionist solution implemented with Artificial Neural Networks, both employed in the task of authorship attribution.
Keywords: Rough set theory, decision rule, rule length, attribute relevance, feature selection, DRSA, ANN, computational stylistics, authorship attribution
