An Environment for Relational Annotation of Political Debates

Blessing, André; Blokker, Nico; Haunss, Sebastian; Kuhn, Jonas; Lapesa, Gabriella; Padó, Sebastian

doi:10.18653/v1/p19-3018

Cited by 6 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Annotation involves first marking claim and actor spans in the text and then selecting the correct categories for the claims and the correct referent for the actor from drop-down lists. See Blessing et al (2019) for details.…”

Section: Computational Construction Of Discourse Networkmentioning

confidence: 99%

Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates

Padó

Blessing

Blokker

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Understanding the structures of political debates (which actors make what claims) is essential for understanding democratic political decision-making. The vision of computational construction of such discourse networks from newspaper reports brings together political science and natural language processing. This paper presents three contributions towards this goal: (a) a requirements analysis, linking the task to knowledge base population; (b) a first release of an annotated corpus of claims on the topic of migration, based on German newspaper reports; (c) initial modeling results.

show abstract

Section: Computational Construction Of Discourse Networkmentioning

confidence: 99%

Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates

Padó

Blessing

Blokker

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The MARDY (Modeling ARgumentation DYnamics in political discourse) annotation environment enables parallel multi-user annotation of texts and the integration of machine learning based annotation (the software components of the MARDY environment are listed in Appendix 1 in the Supplementary File; for a detailed description see Blessing et al, 2019). In the specific study presented here, we use it to annotate political claims in newspaper articles in the German daily quality newspaper taz-die tageszeitung.…”

Section: Mardy: the Task The Challenges And The Annotation Environmentmentioning

confidence: 99%

Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets

Haunss

Kuhn

Padó

et al. 2020

PaG

Self Cite

View full text Add to dashboard Cite

This article investigates the integration of machine learning in the political claim annotation workflow with the goal to partially automate the annotation and analysis of large text corpora. It introduces the MARDY annotation environment and presents results from an experiment in which the annotation quality of annotators with and without machine learning based annotation support is compared. The design and setting aim to measure and evaluate: a) annotation speed; b) annotation quality; and c) applicability to the use case of discourse network generation. While the results indicate only slight increases in terms of annotation speed, the authors find a moderate boost in annotation quality. Additionally, with the help of manual annotation of the actors and filtering out of the false positives, the machine learning based annotation suggestions allow the authors to fully recover the core network of the discourse as extracted from the articles annotated during the experiment. This is due to the redundancy which is naturally present in the annotated texts. Thus, assuming a research focus not on the complete network but the network core, an AI-based annotation can provide reliable information about discourse networks with much less human intervention than compared to the traditional manual approach.

show abstract

“…Table 1 shows the example of three textual snippets containing claims (highlighted in italics), together with their annotation under a DNA-framework (claim category, polarity, actor) from three different debates: the nuclear phaseout debate in Germany after the Fukushima disaster (example 1), the domestic migration debate -the focus of this article (example 2) -and the pension debate (example 3). 1 DNA represents actors and claims as the two types of nodes in a bipartite affiliation network, as shown in Fig. 2.…”

Section: Discourse Network Analysis (Dna)mentioning

confidence: 99%

“…From the full 2015 taz issue, we selected and annotated 959 articles, which all together constitute DEbateNet-mig15, the annotated corpus which is documented in [22] and available as a CLARIN resource. 2 DEbateNet-mig15 has been annotated using MARDY, an environment developed for and shaped by the needs of the Political Science workflow, described in detail in [1].…”

Section: Annotation Workflowmentioning

confidence: 99%

“…The first one is the design of efficient annotation tools which integrate linguistic preprocessing and efficient support for annotators to deal with language data, leading to faster and more reliable annotation. We do not cover this level in the current article; see [1] for a discussion. The second one, in focus here, targets the development of machine learning models which can be applied to novel data to automate (or, more realistically, semi-automate) the workflow.…”

Section: Network Analysis With Machine Learning: First Stepsmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Political Debates through Newspaper Reports: Methods and Outcomes

et al. 2020

Self Cite

View full text Add to dashboard Cite

Discourse network analysis is an aspiring development in political science which analyzes political debates in terms of bipartite actor/claim networks. It aims at understanding the structure and temporal dynamics of major political debates as instances of politicized democratic decision making. We discuss how such networks can be constructed on the basis of large collections of unstructured text, namely newspaper reports. We sketch a hybrid methodology of manual analysis by domain experts complemented by machine learning and exemplify it on the case study of the German public debate on immigration in the year 2015. The first half of our article sketches the conceptual building blocks of discourse network analysis and demonstrates its application. The second half discusses the potential of the application of NLP methods to support the creation of discourse network datasets.

show abstract

An Environment for Relational Annotation of Political Debates

Cited by 6 publications

References 9 publications

Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates

Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates

Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets

Analysis of Political Debates through Newspaper Reports: Methods and Outcomes

Contact Info

Product

Resources

About