On Preference Order of DRSA Conditional Attributes for Computational Stylistics
Computational stylistics (or stylometry) advocates that any writing style can be uniquely defined by quantitative measures. The patterns observed in textual descriptors are specific to authors in such high degree that it enables their recognition. In processing there can be employed techniques from artificial intelligence domain such as Dominance-Based Rough Set Approach (DRSA). Its starting point comprises establishing a preference order in value sets of attributes, which can be dictated by domain knowledge, arbitrarily assumed, or obtained through some analysis. The paper describes the process of finding preference orders through such sequential adjustments that lead to induction of minimal cover decision algorithms with the highest classification accuracy.
KeywordsComputational Stylistics Authorship Attribution DRSA Decision Algorithm Preference Order Conditional Attributes
Unable to display preview. Download preview PDF.
- 1.Abraham, A., Falcón, R., Bello, R. (eds.): Rough Set Theory: A True Landmark in Data Analysis. SCI, vol. 174. Springer, Berlin (2009)Google Scholar
- 2.Argamon, S., Burns, K., Dubnov, S. (eds.): The structure of style: Algorithmic approaches to understanding manner and meaning. Springer, Berlin (2010)Google Scholar
- 3.Craig, H.: Stylistic analysis and authorship studies. In: Schreibman, S., Siemens, R., Unsworth, J. (eds.) A Companion to Digital Humanities. Blackwell, Oxford (2004)Google Scholar
- 8.Stańczyk, U.: Decision rule length as a basis for evaluation of attribute relevance. Journal of Intelligent and Fuzzy Systems 24(3), 429–445 (2013)Google Scholar