Classifying topics and detecting topic shifts in political manifestos


Zirn, Cäcilia ; Glavaš, Goran ; Nanni, Federico ; Eichorts, Jason ; Stuckenschmidt, Heiner


[img]
Preview
PDF
classyman.pdf - Published

Download (236kB)

URL: https://ub-madoc.bib.uni-mannheim.de/41552
Additional URL: http://takelab.fer.hr/poltext2016/PolText2016-proc...
URN: urn:nbn:de:bsz:180-madoc-415521
Document Type: Conference or workshop publication
Year of publication: 2016
Book title: PolText 2016 : The International Conference on the Advances in Computational Analysis of Political Text : proceedings of the conference : sponsored by the European Social Fund, Operational Programme Efficient Human Resources 2014–2020
Page range: 88-93
Conference title: International Conference on the Advances in Computational Analysis of Political Text
Location of the conference venue: Dubrovnik, Croatia
Date of the conference: 14-16 July 2016
Author/Publisher of the book
(only the first ones mentioned)
:
Širinić, Daniela
Place of publication: Zagreb
Publishing house: University of Zagreb
ISBN: 978-953-6457-92-2 , 978-953-184-220-4
Publication language: English
Institution: School of Business Informatics and Mathematics > Praktische Informatik II (Stuckenschmidt 2009-)
School of Business Informatics and Mathematics > Semantic Web (Juniorprofessur) (Ponzetto 2013-15)
Subject: 004 Computer science, internet
Abstract: General political topics, like social security and foreign affairs, recur in electoral manifestos across countries. The Comparative Manifesto Project collects and manually codes manifestos of political parties from all around the world, detecting political topics at sentence level. Since manual coding is time-consuming and allows for annotation inconsistencies, in this work we present an automated approach to topical coding of political manifestos. We first train three independent sentence-level classifiers – one for detecting the topic and two for detecting topic shifts – and then globally optimize their predictions using a Markov Logic network. Experimental results show that the proposed global model achieves high classification performance and significantly outperforms the local sentence-level topic classifier.
Additional information: Online-Ressource

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




+ Citation Example and Export

Zirn, Cäcilia ; Glavaš, Goran ; Nanni, Federico ORCID: 0000-0003-2484-4331 ; Eichorts, Jason ; Stuckenschmidt, Heiner ORCID: 0000-0002-0209-3859 (2016) Classifying topics and detecting topic shifts in political manifestos. Open Access In: PolText 2016 : The International Conference on the Advances in Computational Analysis of Political Text : proceedings of the conference : sponsored by the European Social Fund, Operational Programme Efficient Human Resources 2014–2020 2016 Zagreb [Conference or workshop publication]
[img]
Preview



+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item