License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.LDK.2021.38
URN: urn:nbn:de:0030-drops-145740
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2021/14574/
Go to the corresponding OASIcs Volume Portal

Baumann, Andreas ; Hofmann, Klaus ; Kern, Bettina ; Marakasova, Anna ; Neidhardt, Julia ; Wissik, Tanja

Exploring Causal Relationships Among Emotional and Topical Trajectories in Political Text Data

pdf-format:
OASIcs-LDK-2021-38.pdf (0.6 MB)

Abstract

We explore relationships between dynamics of emotion (arousal and valence) and topical stability in political discourse in two diachronic corpora of Austrian German. In doing so, we assess interactions among emotional and topical dynamics related to political parties as well as interactions between two different domains of discourse: debates in the parliament and journalistic media. Methodologically, we employ unsupervised techniques, time-series clustering and Granger-causal modeling to detect potential interactions. We find that emotional and topical dynamics in the media are only rarely a reflex of dynamics in parliamentary discourse.

BibTeX - Entry

@InProceedings{baumann_et_al:OASIcs.LDK.2021.38,
  author =	{Baumann, Andreas and Hofmann, Klaus and Kern, Bettina and Marakasova, Anna and Neidhardt, Julia and Wissik, Tanja},
  title =	{{Exploring Causal Relationships Among Emotional and Topical Trajectories in Political Text Data}},
  booktitle =	{3rd Conference on Language, Data and Knowledge (LDK 2021)},
  pages =	{38:1--38:8},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-199-3},
  ISSN =	{2190-6807},
  year =	{2021},
  volume =	{93},
  editor =	{Gromann, Dagmar and S\'{e}rasset, Gilles and Declerck, Thierry and McCrae, John P. and Gracia, Jorge and Bosque-Gil, Julia and Bobillo, Fernando and Heinisch, Barbara},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/14574},
  URN =		{urn:nbn:de:0030-drops-145740},
  doi =		{10.4230/OASIcs.LDK.2021.38},
  annote =	{Keywords: time-series clustering, Granger causality, topical stability, emotion, political discourse}
}

Keywords: time-series clustering, Granger causality, topical stability, emotion, political discourse
Collection: 3rd Conference on Language, Data and Knowledge (LDK 2021)
Issue Date: 2021
Date of publication: 30.08.2021

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI