Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections

Abstract

Political campaigns are full of political ads posted by candidates on social media. Political advertisements constitute a basic form of campaigning, subjected to various social requirements. We present the first publicly open dataset for detecting specific text chunks and categories of political advertising in the Polish language. It contains 1,705 human-annotated tweets tagged with nine categories, which constitute campaigning under Polish electoral law. We achieved a 0.65 inter-annotator agreement (Cohen′s kappa score). An additional annotator resolved the mismatches between the first two annotators improving the consistency and complexity of the annotation process. We used the newly created dataset to train a well established neural tagger (achieving a 70% percent points F1 score). We also present a possible direction of use cases for such datasets and models with an initial analysis of the Polish 2020 Presidential Elections on Twitter.

Publication
Proceedings of the The Fourth Widening Natural Language Processing Workshop
Łukasz Augustyniak
Łukasz Augustyniak
PhD Student

Data Scientist, Machine Learning Engineer, Lawyer.

Krzysztof Rajda
Krzysztof Rajda
PhD Student

My research interests includes NLP and social media analysis.

Tomasz Kajdanowicz
Tomasz Kajdanowicz
Associate Professor, head of faculty’s doctoral studies, head of department

My research interests include representation learning, social network and media analysis, and machine learning.

Related