Detailed Information on Publication Record
2024
Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis
HORÁK, Aleš, Radoslav SABOL, Ondřej HERMAN and Vít BAISABasic information
Original name
Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis
Authors
HORÁK, Aleš (203 Czech Republic, guarantor, belonging to the institution), Radoslav SABOL (703 Slovakia, belonging to the institution), Ondřej HERMAN (203 Czech Republic, belonging to the institution) and Vít BAISA (203 Czech Republic, belonging to the institution)
Edition
Expert Systems with Applications, Elsevier, 2024, 0957-4174
Other information
Language
English
Type of outcome
Článek v odborném periodiku
Field of Study
10200 1.2 Computer and information sciences
Country of publisher
United States of America
Confidentiality degree
není předmětem státního či obchodního tajemství
References:
Impact factor
Impact factor: 8.500 in 2022
Organization unit
Faculty of Informatics
UT WoS
001235661700001
Keywords in English
propaganda; disinformation; manipulative techniques; text style analysis; benchmark dataset
Tags
International impact, Reviewed
Změněno: 14/9/2024 10:14, doc. RNDr. Aleš Horák, Ph.D.
Abstract
V originále
Public texts aiming at reader manipulation for propaganda or disinformation purposes pose a significant threat to society. The ability to detect the presence of a specific manipulative technique in a text offers an informed warning to readers and guides them to carefully judge the actual statement. In this article, we address the problem of developing new models capable of analyzing newspaper articles for propagandistic features. We introduce a new large dataset of manipulative techniques obtained via gathering and human annotation of 8,646 newspaper articles in Czech, which represents one of the former Soviet influence area languages. The dataset allows both to train new methods to recognize propaganda and disinformation and offer a general comparable benchmark for the techniques. We evaluate the dataset against selected state-of-the-art machine learning approaches to provide high-performing baselines for detecting seventeen annotated manipulative techniques. We also present thorough measurements of inter-annotator agreements that approximate the difficulty level of each of the attributes. As a new finding, we propose a set of text style analysis features that lean on the assumption that each manipulation leads to a specific style pattern. We show that the style analysis improves the detection results for most of the manipulative techniques. The viability of the approach is also confirmed on the well-known QProp propaganda dataset, providing new state-of-the-art results.
Links
| LM2023062, research and development project |
|