19. századi magyar regényeken végzett kísérletek a magyar nyelvű szerzőazonosítás leghatékonyabb távolságméréseinek megtalálására

Mária Timári; ELTE DH

Tímea Borbála Bajzát; ELTE DH

Gábor Palkó; ELTE BTK TI Digitális Bölcsészeti Tanszék, Digitális Örökség Nemzeti Laboratórium, BTK Irodalomtudományi Intézet

NETWORKSHOP

2021-10-09 09:32:06

In the field of computational stylistics it is a widespread assumption that there exists a unique pattern of a person’s language use and this is a socalled authorial fingerprint (Baayen et al. 2002). Identifying the authorial fingerprint can become a base of using quantitative text similarity studies for authorship attribution. Although the metaphor of the “fingerprint” may give the false impression that this pattern can be read from the author’s texts in an objective way. The modelling of this “fingerprint” is in fact a creative digital humanities task which constructs a pattern that is based on a selection and combination of dozens of linguistic features that can be interpreted statistically and that can only be interpreted in comparison with other authorial texts.Considering the size of the corpora and the complexity of text characteristics and similarity calculations, the method cannot be done without the use of computer algorithms. There are already some softwares (e.g. R-Stylo, JGAAP, Websty) that apparently offer an accessible way to researchers for analyzing texts, (however these methods limit the process of searching for patterns), while on the other hand it is possible to implement the calculations using custom program codes.In our research we endeavour to find the most efficient measures in authorship attribution for Hungarian texts.https://doi.org/10.31915/NWS.2021.9

magyar

Peer-reviewed Paper

application/pdf

http://ocs.mtak.hu/index.php/nws/2021/paper/view/68

NETWORKSHOP; NETWORKSHOP 2021

Authors who submit to this conference agree to the following terms:<br/> <strong>a)</strong>&nbsp;Authors retain copyright over their work, while allowing the conference to place this unpublished work under a <a href="http://creativecommons.org/licenses/by/3.0/">Creative Commons Attribution License</a>, which allows others to freely access, use, and share the work, with an acknowledgement of the work's authorship and its initial presentation at this conference.<br/> <strong>b)</strong>&nbsp;Authors are able to waive the terms of the CC license and enter into separate, additional contractual arrangements for the non-exclusive distribution and subsequent publication of this work (e.g., publish a revised version in a journal, post it to an institutional repository or publish it in a book), with an acknowledgement of its initial presentation at this conference.<br/> <strong>c)</strong>&nbsp;In addition, authors are encouraged to post and share their work online (e.g., in institutional repositories or on their website) at any point before and after the conference.