Abstract
Data mining has emerged to address the problem of transforming data into useful knowledge. Although most data mining techniques, such as the use of association rules, may substantially reduce the search effort over large data sets, often, the consequential outcomes surpass the amount of information humanly manageable. On the other hand, important association rules may be overlooked owing to the setting of the support threshold, which is a very subjective metric, but rooted in most data mining techniques. This paper presents a study on the effects, in terms of precision and recall, of using a data preparation technique, called SemPrune, which is built on domain ontology. SemPrune is intended for pre- and post-processing phases of data mining. Identifying generalization/specialization relations, as well as composition/decomposition relations, is the key to successfully applying SemPrune.