Authorship Verification based on Syntax Features

RYGL, Jan, Kristýna ZEMKOVÁ and Vojtěch KOVÁŘ. Authorship Verification based on Syntax Features. In Aleš Horák, Pavel Rychlý. Proceedings of the Sixth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2012. 1st ed. Brno (Czech Republic): Tribun EU, 2012, p. 111-119. ISBN 978-80-263-0313-8.

Basic information

• Original name: Authorship Verification based on Syntax Features
• Authors: RYGL, Jan (203 Czech Republic, guarantor, belonging to the institution), Kristýna ZEMKOVÁ (203 Czech Republic, belonging to the institution) and Vojtěch KOVÁŘ (203 Czech Republic, belonging to the institution).
• Edition: 1st ed. Brno (Czech Republic), Proceedings of the Sixth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2012, p. 111-119, 9 pp. 2012.
• Publisher: Tribun EU

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 60200 6.2 Languages and Literature
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: printed version "print"
• WWW: paper conference page
• RIV identification code: RIV/00216224:14330/12:00062288
• Organization unit: Faculty of Informatics
• ISBN: 978-80-263-0313-8
• Keywords (in Czech): ověřování autorství;syntaktická analýza;SET;strojové učení
• Keywords in English: authorship verification;syntactic analysis;SET;machine learning
• Tags: International impact

Abstract

Authorship verification is wildly discussed topic at these days. In the authorship verification problem, we are given examples of the writing of an author and are asked to determine if given texts were or were not written by this author. In this paper we present an algorithm using syntactic analysis system SET for verifying authorship of the documents. We propose three variants of two-class machine learning approach to authorship verification. Syntactic features are used as attributes in suggested algorithms and their performance is compared to established word-lenth distribution features. Results indicate that syntactic features provide enough information to improve accuracy of authorship verification algorithms.

Links

• VF20102014003, research and development project: Name: Analýza přirozeného jazyka v prostředí internetu (Acronym: APJI)

Investor: Ministry of the Interior of the CR