Who are They Talking About? Detecting Mentions of Social Groups in Political Texts with Supervised Learning

Hauke Licht () and Ronja Sczepanksi ()
Additional contact information
Hauke Licht: University of Cologne, Cologne Center for Comparative Politics
Ronja Sczepanksi: Sciences Po Paris, Center for European Studies and Comparative Research

No 277, ECONtribute Discussion Papers Series from University of Bonn and University of Cologne, Germany

Abstract: Politicians appeal to social groups to court their electoral support. However, quantifying which groups politicians refer to, claim to represent, or address in their public communication presents researchers with challenges. We propose a novel supervised learning approach for extracting group mentions in political texts. We first collect human annotations to determine the exact text passages that refer to social groups. We then fine-tune a Transformer language model for contextualized supervised classification at the word level. Applied to unlabeled texts, our approach enables researchers to automatically detect and extract word spans that contain group mentions. We illustrate our approach in three applications, generating new empirical insights how British parties use social groups in their rhetoric. Our methodological innovation allows to detect and extract mentions of social groups from various sources of texts, creating new possibilities for empirical research in political science.

Keywords: social groups; political rhetoric; computational text analysis; supervised classification (search for similar items in EconPapers)
JEL-codes: C45 (search for similar items in EconPapers)
Pages: 54 pages
Date: 2024-02
New Economics Papers: this item is included in nep-big, nep-cdm, nep-cmp and nep-pol
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econtribute.de/RePEc/ajk/ajkdps/ECONtribute_277_2024.pdf First version, 2024 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajk:ajkdps:277

Access Statistics for this paper

More papers in ECONtribute Discussion Papers Series from University of Bonn and University of Cologne, Germany Niebuhrstrasse 5, 53113 Bonn, Germany.
Bibliographic data for series maintained by ECONtribute Office ().