Thesis Details

Strojové učení v oblasti stylometrie a určování autorství

Bachelor's Thesis Student: Drápela Karel Academic Year: 2015/2016 Supervisor: Smrž Pavel, doc. RNDr., Ph.D.
English title
Machine Learning in the Domain of Stylometry and Authorship Attribution
Language
Czech
Abstract

Thesis deals with authorship attribution of english internet comments. It describes state of art in authorship attribution on social networks. It decsribes how the new system created during the work on this thesis functions. System is based on selection of most informative characteristics mostly from character n-grams and part of speech tags. It presents results of testing on comments from social networks Quora and Twitter.

Keywords

authorship attribution, machine learning, feature selection, quora, twitter

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade B
Date
15 June 2016
Reviewer
Škoda Petr, RNDr.
Committee
Meduna Alexander, prof. RNDr., CSc. (DIFS FIT BUT), předseda
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Křivka Zbyněk, Ing., Ph.D. (DIFS FIT BUT), člen
Citation
DRÁPELA, Karel. Strojové učení v oblasti stylometrie a určování autorství. Brno, 2016. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2016-06-15. Supervised by Smrž Pavel. Available from: https://www.fit.vut.cz/study/thesis/18623/
BibTeX 
@bachelorsthesis{FITBT18623,
    author = "Karel Dr\'{a}pela",
    type = "Bachelor's thesis",
    title = "Strojov\'{e} u\v{c}en\'{i} v oblasti stylometrie a ur\v{c}ov\'{a}n\'{i} autorstv\'{i}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2016,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/18623/"
}

Theses

Back to top