@ARTICLE{Stańczyk_Urszula_Data_2021, author={Stańczyk, Urszula and Zielosko, Beata}, volume={69}, number={4}, journal={Bulletin of the Polish Academy of Sciences Technical Sciences}, pages={e137629}, howpublished={online}, year={2021}, abstract={When patterns to be recognised are described by features of continuous type, discretisation becomes either an optional or necessary step in the initial data pre-processing stage. Characteristics of data, distribution of data points in the input space, can significantly influence the process of transformation from real-valued into nominal attributes, and the resulting performance of classification systems employing them. If data include several separate sets, their discretisation becomes more complex, as varying numbers of intervals and different ranges can be constructed for the same variables. The paper presents research on irregularities in data distribution, observed in the context of discretisation processes. Selected discretisation methods were used and their effect on the performance of decision algorithms, induced in classical rough set approach, was investigated. The studied input space was defined by measurable style-markers, which, exploited as characteristic features, facilitate treating a task of stylometric authorship attribution as classification}, type={Article}, title={Data irregularities in discretisation of test sets used for evaluation of classification systems: A case study on authorship attribution}, URL={http://www.journals.pan.pl/Content/119904/PDF/17_01628_Bpast.No.69(4)_27.08.21_druk.pdf}, doi={10.24425/bpasts.2021.137629}, keywords={discretisation, data irregularities, evaluation and test sets, rough sets, authorship attribution, stylometry}, }