Informace o publikaci

Augmenting Stylometric Features to Improve Detection of Propaganda and Manipulation

Autoři

SABOL Radoslav HORÁK Aleš

Rok publikování 2023
Druh Článek ve sborníku
Konference Proceedings of the Seventeenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2023
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Klíčová slova stylometry; propaganda detection; manipulative style analysis; Propaganda dataset; Czech
Popis Identification of manipulative techniques in newspaper texts allows an informed reader to cope with the text content without being negatively influenced. In this paper, we present new developments in using stylometry to support a deep learning neural network model in labelling newspaper articles for the presence of specific manipulative techniques. We also evaluate all stylometric features in 16 groups and improve the manipulation detection results in 15 of 17 techniques.
Související projekty:

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

Další info