Style & Identity Recognition

D 2015

Style & Identity Recognition

RYGL, Jan

Základní údaje

Originální název

Style & Identity Recognition

Autoři

RYGL, Jan (203 Česká republika, garant, domácí)

Vydání

Brno, Ninth Workshop on Recent Advances in Slavonic Natural Language Processing, od s. 3-10, 8 s. 2015

Nakladatel

Tribun EU

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

paper

Kód RIV

RIV/00216224:14330/15:00085163

Organizační jednotka

Fakulta informatiky

ISBN

978-80-263-0974-1

ISSN

Klíčová slova anglicky

stylometry; authorship recognition; machine learning; open-source

Změněno: 26. 5. 2021 18:07, RNDr. Jan Rygl

Anotace

V originále

Knowledge of the author’s identity and style can by used in the fight against forged and and anonymous documents and illegal actions in the Internet. Nowadays, there are many systems dedicated to solving stylometric tasks, but they are predominantly designed only for a specific task; they are used exclusively by their owners; or they do not natively support any Slavic languages. Therefore, we present new open-source modular system Style & Identity Recognition (SIR). The system is designed to support any stylometric tasks with minimal efforts (or event by default) by combining dynamic stylometry features selection and prediction driven by input data labels. The system is free for non-commercial applications and easy to use, therefore it can be helpful for people dealing with threatening e-mails or sms, children forum protection against pedophiles and other tasks. Being customizable and freely accessible, it can be also used as a baseline for other systems solving stylometry tasks. System combines machine learning techniques and nature language processing tools. It is written in Python and it is dependent on other open-source Python libraries.

Návaznosti

LM2010013, projekt VaV

Název: LINDAT-CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat (Akronym: LINDAT-Clarin)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Projekt LINDAT-Clarin - Vybudování a provoz českého uzlu pan-evropské infrastruktury pro výzkum

Citovat

RYGL, Jan. Style & Identity Recognition. In Aleš Horák, Pavel Rychlý, Adam Rambousek. Ninth Workshop on Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2015, s. 3-10. ISBN 978-80-263-0974-1.

@inproceedings{1320589,
   author = {Rygl, Jan},
   address = {Brno},
   booktitle = {Ninth Workshop on Recent Advances in Slavonic Natural Language Processing},
   editor = {Aleš Horák, Pavel Rychlý, Adam Rambousek},
   keywords = {stylometry; authorship recognition; machine learning; open-source},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Brno},
   isbn = {978-80-263-0974-1},
   pages = {3-10},
   publisher = {Tribun EU},
   title = {Style & Identity Recognition},
   url = {https://nlp.fi.muni.cz/raslan/2015/paper06-Rygl.pdf},
   year = {2015}
}

TY  - CONF
ID  - 1320589
AU  - Rygl, Jan
PY  - 2015
TI  - Style & Identity Recognition
PB  - Tribun EU
CY  - Brno
SN  - 9788026309741
KW  - stylometry
KW  - authorship recognition
KW  - machine learning
KW  - open-source
UR  - https://nlp.fi.muni.cz/raslan/2015/paper06-Rygl.pdf
N2  - Knowledge of the author’s identity and style can by used in the fight against forged and and anonymous documents and illegal actions in the Internet. Nowadays, there are many systems dedicated to solving stylometric tasks, but they are predominantly designed only for a specific task; they are used exclusively by their owners; or they do not natively support any Slavic languages. Therefore, we present new open-source modular system Style & Identity Recognition (SIR). The system is designed to support any stylometric tasks with minimal efforts (or event by default) by combining dynamic stylometry features selection and prediction driven by input data labels. The system is free for non-commercial applications and easy to use, therefore it can be helpful for people dealing with threatening e-mails or sms, children forum protection against pedophiles and other tasks. Being customizable and freely accessible, it can be also used as a baseline for other systems solving stylometry tasks. System combines machine learning techniques and nature language processing tools. It is written in Python and it is dependent on other open-source Python libraries.
ER  -

RYGL, Jan. Style \&{} Identity Recognition. In Aleš Horák, Pavel Rychlý, Adam Rambousek. \textit{Ninth Workshop on Recent Advances in Slavonic Natural Language Processing}. Brno: Tribun EU, 2015, s.~3-10. ISBN~978-80-263-0974-1.

Přehled o publikaci