A Framework for Authorship Identification in the Internet Environment

Varování

Publikace nespadá pod Pedagogickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

RYGL Jan HORÁK Aleš

Rok publikování 2011
Druh Článek ve sborníku
Konference Proceedings of Fifth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2011
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Obor Využití počítačů, robotika a její aplikace
Klíčová slova authorship identification;authorship similarity
Popis Misuse of anonymous online communication for illegal purposes has become a major concern. In this paper, we present a framework named ART (Authorship Recognition Tool), that is designed to minimize manual procedures and maximize the efficiency of authorship identification based on the content of Internet electronic documents. The framework covers the phases of document retrieval and database document management. ART provides implementations of efficient authorship identification algorithm and authorship similarity algorithm including the possibility to obtain extra data for learning and tests. The framework also determines whether or not different author’s identities are interlinked. The authorship is analysed by machine learning and natural language processing methods. Technical information such as IP address is considered only as an optional attribute for the machine learning because it can be easily forged or devalued if the author communicates from public places or through proxy servers.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.