@article{Tambouratzis01062004,
author = "Ταμπουρατζής, Γιώργος and Μαρκαντωνάτου, Στέλλα and Hairetakis, N. and Βασιλείου, Μαρίνα and Καραγιάννης, Γεώργιος and Tambouratzis, D.",
abstract = "This article describes a method for discriminating among authors within a given register of Modern Greek. The focus here is to determine to what extent the stylistic differences among authors can be detected with a high degree of accuracy for a set of texts belonging to a well?defined register. To that end, the chosen register is characterized by a well?defined sub?language, from which a corpus of more than 1,000 documents has been created. To discriminate the texts according to author style, a series of experiments have been performed using statistical techniques. Each text has been represented by a vector covering several linguistic aspects, in an effort to determine the most effective style markers. The experimental results indicate that the proposed approach can successfully separate the author styles for a given register. An extensive study of the effectiveness of the different variable categories has been performed. For instance, diglossia information on its own is not sufficient for author discrimination. Instead, a systematic evaluation process indicates that part?of?speech, structural and algorithmically derived lemma?frequency variables are the most important style markers, their use leading to an author discrimination accuracy exceeding 90%.",
doi = "10.1093/llc/19.2.221",
journal = "Literary and Linguistic Computing",
number = "2",
pages = "221-242",
title = "{D}iscriminating the {R}egisters and {S}tyles in the {M}odern {G}reek {L}anguage-Part 2: {E}xtending the {F}eature {V}ector to {O}ptimize {A}uthor {D}iscrimination ",
url = "http://llc.oxfordjournals.org/content/19/2/221.abstract",
volume = "19",
year = "2004",
}