BibTeX
@article{blokker:_between,
abstract = {Newspaper reports provide a rich source of information on the unfolding of public debates, which can serve as basis for inquiry in political science. Such debates are often triggered by critical events, which attract public attention and incite the reactions of political actors: crisis sparks the debate. However, due to the challenges of reliable annotation and modeling, few large-scale datasets with high-quality annotation are available. This paper introduces DebateNet2.0, which traces the political discourse on the 2015 European refugee crisis in the German quality newspaper taz. The core units of our annotation are political claims (requests for specific actions to be taken) and the actors who advance them (politicians, parties, etc.). Our contribution is twofold. First, we document and release DebateNet2.0 along with its companion R package, mardyR. Second, we outline and apply a Discourse Network Analysis (DNA) to DebateNet2.0, comparing two crucial moments of the policy debate on the ârefugee crisisâ: the migration flux through the Mediterranean in April/May and the one along the Balkan route in September/October. We guide the reader through the methods involved in constructing a discourse network from a newspaper, demonstrating that there is not one single discourse network for the German migration debate, but multiple ones, depending on the research question through the associated choices regarding political actors, policy fields and time spans.},
added-at = {2021-11-22T08:09:12.000+0100},
author = {Blokker, Nico and Blessing, Andre and Dayanik, Erenay and Kuhn, Jonas and Pad{ó}, Sebastian and Lapesa, Gabriella},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c17511a37e3ad0d3d416c2b7041e972d/sp},
interhash = {1942e48042e3ead163e5b2cd226baec5},
intrahash = {c17511a37e3ad0d3d416c2b7041e972d},
journal = {Language Resources and Evaluation},
keywords = {article myown},
pages = {121-153},
timestamp = {2023-05-11T17:11:35.000+0200},
title = {Between welcome culture and border fence: The {E}uropean refugee crisis in {G}erman newspaper reports},
url = {https://doi.org/10.1007/s10579-023-09641-8},
volume = 57,
year = 2023
}
@InProceedings{blokker22:_why_justif_claim_matter_under_party_posit,
author = {Nico Blokker and Tanise Ceron and Andre Blessing and Erenay Dayanik and Sebastian Haunss and Jonas Kuhn and Gabriella Lapesa and Sebastian Padó},
title = {Why Justifications of Claims Matter for Understanding Party Positions},
keywords = {myown workshop},
booktitle = {Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis},
url = {https://old.gscl.org/media/pages/arbeitskreise/cpss/cpss-2022/workshop-proceedings-2022/254133848-1662996909/cpss-2022-proceedings.pdf},
year = 2022}
@InProceedings{blokker20:_swimm_tide,
added-at = {2020-10-02T09:43:59.000+0200},
address = {Online},
author = {Blokker, Nico and Dayanik, Erenay and Lapesa, Gabriella and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c8caad10654ddbc031a19634a4204f7a/sp},
booktitle = {Proceedings of the {NLP+CSS} workshop},
interhash = {9399eb41d74c6c2be84a191bfa6d1885},
intrahash = {c8caad10654ddbc031a19634a4204f7a},
keywords = {myown workshop},
pages = {24-34},
timestamp = {2020-11-11T21:06:25.000+0100},
title = {Swimming with the Tide? Positional Claim Detection across Political Text Types},
url = {https://www.aclweb.org/anthology/2020.nlpcss-1.3/},
year = 2020
}
@InProceedings{dayanik21:_using_hierar_class_struc_improv,
added-at = {2021-06-01T20:41:13.000+0200},
address = {Bangkok, Thailand},
author = {Dayanik, Erenay and Blessing, Andre and Blokker, Nico and Haunss, Sebastian and Kuhn, Jonas and Lapesa, Gabriella and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20f6d2fc4aa639e7210990201291d5a5c/sp},
booktitle = {Proceedings of the ACL Workshop of Structured Prediction},
interhash = {dd2830015fb7948b28906be22cd03a64},
intrahash = {0f6d2fc4aa639e7210990201291d5a5c},
keywords = {myown workshop},
timestamp = {2021-08-05T19:17:39.000+0200},
title = {Using Hierarchical Class Structure to Improve Fine-Grained Claim Classification},
url = {https://aclanthology.org/2021.spnlp-1.6/},
year = 2021
}
@InProceedings{dayanik22:improving,
author = {Erenay Dayanik and Andre Blessing and Nico Blokker and Sebastian Haunss and Jonas Kuhn and Gabriella Lapesa and Sebastian Padó},
title = {Improving Neural Political Statement Classification with Class Hierarchical Information},
keywords = {conference myown preprint},
booktitle = {Findings of ACL},
year = 2022,
pages = "2367-2382",
note = {Acceptance rate: 31.4 url = {https://aclanthology.org/2022.findings-acl.186},
address = {Dublin, Ireland},
}
@InProceedings{dayanik20:_maskin_actor_infor_leads_fairer,
abstract = {A central concern in Computational Social Sciences (CSS) is fairness: where the role of NLP is to scale up text analysis to large corpora, the quality of automatic analyses should be as independent as possible of textual properties. We analyze the performance of a state-of-the-art neural model on the task of political claims detection (i.e., the identification of forward-looking statements made by political actors) and identify a strong frequency bias: claims made by frequent actors are recognized better. We propose two simple debiasing methods which mask proper names and pronouns during training of the model, thus removing personal information bias. We find that (a) these methods significantly decrease frequency bias while keeping the overall performance stable; and (b) the resulting models improve when evaluated in an out-of-domain setting.},
added-at = {2020-04-04T15:05:44.000+0200},
address = {Online},
author = {Dayanik, Erenay and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23293989e68e3eda1db5018a5ac18dee4/sp},
booktitle = {Proceedings of ACL},
interhash = {00061c6a1cf89353a1c20cb29b483974},
intrahash = {3293989e68e3eda1db5018a5ac18dee4},
keywords = {conference myown},
pages = {4385-4391},
timestamp = {2020-12-07T16:42:14.000+0100},
title = {Masking Actor Information Leads to Fairer Political Claims Detection},
url = {https://www.aclweb.org/anthology/2020.acl-main.404/},
year = 2020
}
@InProceedings{dayanik21:_disen_docum_topic_author_gender_multip_languag,
added-at = {2021-02-23T10:08:29.000+0100},
author = {Dayanik, Erenay and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29f3e2e70efa78c0dd97ae2f4b2f071ac/sp},
booktitle = {Proceedings of the EACL WASSA workshop},
interhash = {e172465d2cf0dd67ab27a810d641f629},
intrahash = {9f3e2e70efa78c0dd97ae2f4b2f071ac},
keywords = {myown workshop},
pages = {40-49},
timestamp = {2021-04-21T15:24:46.000+0200},
title = {Disentangling Document Topic and Author Gender in Multiple Languages: Lessons for Adversarial Debiasing},
url = {https://www.aclweb.org/anthology/2021.wassa-1.6},
year = 2021
}
@article{dayanik22:_better_under_bias_nlp_model,
author = {Erenay Dayanik and Thang Vu and Sebastian Padó},
title = {Bias Identification and Attribution in {NLP} Models with Regression and Effect Sizes},
keywords = {article myown},
journal = {Northern European Journal of Language Technology},
year = {2022},
number = {1},
volume = {8},
url = {https://doi.org/10.3384/nejlt.2000-1533.2022.3505}}
@article{haunss20:_integ_manual_autom_annot_creat,
abstract = {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.},
added-at = {2020-03-23T20:19:19.000+0100},
author = {Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Lapesa, Gabriella},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24dcbda0eb92af231eef2b033d8d51b23/sp},
interhash = {31dfa8365630383946e268e14bca9968},
intrahash = {4dcbda0eb92af231eef2b033d8d51b23},
journal = {Politics and Governance},
keywords = {article myown},
number = 2,
timestamp = {2020-06-02T16:24:19.000+0200},
title = {Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets},
url = {https://dx.doi.org/10.17645/pag.v8i2.2591},
volume = 8,
year = 2020
}
@article{lapesa20:_analy_polit_debat_newsp_repor,
abstract = {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.},
added-at = {2020-05-29T15:45:59.000+0200},
author = {Lapesa, Gabriella and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24226ed780f206d3d17058c3482f81bf1/sp},
interhash = {cfd5940a96a17ad172311fe643cff81b},
intrahash = {4226ed780f206d3d17058c3482f81bf1},
journal = {Datenbank-Spektrum},
keywords = {article myown},
number = 2,
timestamp = {2020-06-18T16:40:56.000+0200},
title = {Analysis of Political Debates through Newspaper Reports: Methods and Outcomes},
url = {https://dx.doi.org/10.1007/s13222-020-00344-w},
volume = 20,
year = 2020
}
@InProceedings{lapesa2020debatenetmig15,
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.},
added-at = {2020-02-11T14:44:55.000+0100},
address = {Online},
author = {Lapesa, Gabriella and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23e4f84069e33ea38700b4b9e36f6e61e/sp},
booktitle = {Proceedings of LREC},
interhash = {351c134387fd9e594c83bc773b14529e},
intrahash = {3e4f84069e33ea38700b4b9e36f6e61e},
keywords = {conference myown},
pages = {919-927},
timestamp = {2020-12-07T16:42:49.000+0100},
title = {{DEbateNet-mig15}: {T}racing the 2015 Immigration Debate in {G}ermany Over Time},
url = {https://www.aclweb.org/anthology/2020.lrec-1.115},
year = 2020
}
@InProceedings{pado19:_who_sides_with_whom,
author = {Sebastian Padó and Andre Blessing and Nico Blokker and Erenay Dayanik and Sebastian Haunss and Jonas Kuhn},
title = {Who Sides With Whom? Towards Computational Construction of Discourse Networks for Political Debates},
booktitle = {Proceedings of ACL},
keywords = {conference myown},
year = 2019,
address = {Florence, Italy}}