出版社：Polish Academy of Sciences, UNESCO Chair for Translation Studies and Intercultural Communication of the Jagiellonian University, Kraków
摘要：Th e present study addresses one of the theoretical problems of computer-assisted authorship attribution, namely the question which traceable features of language can betray authorial uniqueness (a stylistic fi ngerprint) of literary texts. A number of recent approaches show that apart from lexical measures — especially those relying on the frequencies of the most frequent words — also some other features of written language are considerably eff ective as discriminators of authorial style. However, there have been no attempts to compare the attribution potential of these features. Th e aim of the present study, then, was to examine the eff ectiveness of several style-markers in authorship attribution. Th e style-markers chosen for the empirical investigation are those that can be retrieved from a non-lemmatized corpus of plain text fi les, such as the most frequent words, word bi-grams, diff erent letter sequences, and markers of diff erent nature, combined in one sample. Equally important, however, was to compare usefulness of the chosen style-markers across a few languages: English, Polish, German, and Latin. Th e results confi rmed a high attribution eff ectiveness of word-based style-markers in the English corpus, but the alternative markers are shown to be usually more eff ective in the other languages.
关键词：authorship attribution; stylometry; style-markers; multidimensional methods; Delta method;controlled attribution test
