DEbateNet-mig15:Tracing the 2015 Immigration Debate in Germany Over Time

15811

Authors

nan

Abstract

AbstractDEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate

Keywords

nan

Full Content

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 919–927 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 919 DEbateNet-mig15: Tracing the 2015 Immigration Debate in Germany Over Time Gabriella Lapesa1, André Blessing1, Nico Blokker2, Erenay Dayanik1, Sebastian Haunss2, Jonas Kuhn1, Sebastian Padó1 Institute for Natural Language Processing1, University of Stuttgart (Germany) Research Center for Inequality and Social Policy2, University of Bremen (Germany) name.surname@ims.uni-stuttgart.de, name.surname@uni-bremen.de Abstract DEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate. Keywords: computational social science, discourse network analysis, political science, annotation, interdisciplinarity 1. Introduction The last decade has witnessed a dramatic increase in the number of refugees attempting to enter Europe from Africa and the Middle East. This rise in numbers has had a huge impact on society, thereby strongly resonating in the public debate. Is it right to open the borders to immigrants, or should migration be more strictly regulated? To what extent should host countries be responsible for accommodating refugees? What are the implications for internal security and economy? This is just a small sample of the questions which characterize the public debate on immigration, both at the level of single individuals (the citizens) and public institutions (politicians). From a political science perspective, a crucial aspect of the discourse concerning societally relevant topics is repre- sented by its dynamics. For example, one highly influential political actor may change her/his mind about a specific issue within the domain of interest (e.g., should we establish a quota for refugees?), and initiate a change in the opinion of other discourse participants who, in turn, may converge on the same position or take a strong stand against it. Such dynamics lead to the emergence of new political coalitions and to the disappearence of others. Empirically, political discourse is represented in terms of a network of actors and their statements concerning relevant aspects of the discourse domain (e.g., Angela Merkel, actor, declares that the borders should stay open for refugees; a far-right political party, ac- tor, states exactly the opposite). This abstract representation allows for an empirical investigation of the unfolding of the debate over time, which can be captured in terms of the quantitative properties of the network (Haunss and Kohlmor- gen, 2009; Leifeld and Haunss, 2012; Haunss …

Content truncated to 500 words

Labeled Text

AbstractDEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate

Publication Details

Paper ID:
15811
Year:
2020
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan