|
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
|
ORCID: 0000-0003-2484-4331 ; Eichorts, Jason ; Stuckenschmidt, Heiner 
Širinić, Daniela
88-93
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
International Conference on the Advances in Computational Analysis of Political Text
(Dubrovnik, Croatia)
[Conference or workshop publication]
Search Authors in
