Article published in:From Text to Political Positions: Text analysis across disciplines
Edited by Bertie Kaal, Isa Maks and Annemarie van Elfrinkhof
[Discourse Approaches to Politics, Society and Culture 55] 2014
► pp. 93–116
Text to Ideology or Text to Party Status?
Graeme Hirst | Department of Computer Science, University of Toronto
Yaroslav Riabinin | Department of Computer Science, University of Toronto
Jory Graham | Department of Computer Science, University of Toronto
Magali Boizot-Roche | Department of Computer Science, University of Toronto
Colin Morris | Department of Computer Science, University of Toronto
Recent papers have used support-vector machines with word features to classify political texts by ideology. Our own work on this topic led us to hypothesize that such classifiers are sensitive not to expressions of ideology but rather to expressions of attack and defense, opposition and government. We test this hypothesis by training on one set of parliamentary speeches and testing on another in which party roles have been interchanged, and we find that the performance of the classifier completely disintegrates. Moreover, some features that are indicative of each party ‘swap sides’ with the change of government. Our results suggest that the language of attack and defense, of government and opposition, will dominate and confound any sensitivity to ideology in these kinds of classifiers.
Published online: 07 May 2014
(2009) Actes de l’atelier de clôture de la cinquième édition du DÉfi Fouille de Textes, Paris, 22 June 2009.
Diermeier, D., J.-F. Godbout, B. Yu and S. Kaufmann
2007 Language and ideology in Congress. Annual Meeting of the Midwest Political Science Association.
Forest, D., A. van Hoeydonck, D. Létourneau and M. Bélanger
2009 Impacts de la variation du nombre de traits discriminants sur la catégorisation des documents. Actes de l’atelier de clôture de la cinquième édition du DÉfi Fouille de Textes, Paris, 22 June 2009, pp. 75–88.
2001 Aligned Hansards of the 36th Parliament of Canada. Available at www.isi.edu/natural-language/download/hansard/
2007 Spin: Lexical semantics, transitivity, and the identification of implicit sentiment. PhD thesis, University of Maryland, College Park.
Grouin, C., B. Arnulphy, J.-B. Berthelin, S. El Ayari, A. Garcia-Fernandez, A. Grappy, M. Hurault-Plantet, P. Paroubek, I. Robba and P. Zweigenbaum
2009 Présentation de l’édition du D’Efi Fouille de Textes (DEFT’09). Actes de l’atelier de clôture de la cinquième édition du DÉfi Fouille de Textes, Paris, 22 June 2009, pp. 35–50.
Hix, S., A.G. Noury and G. Roland
Jiang, M. and S. Argamon
2008 Political leaning categorization by exploring subjectivities in political blogs. Proceedings, 4th International Conference on Data Mining (DMIN 2008), pp. 647–653.
Lin, W., T. Wilson, J. Wiebe and A. Hauptmann
2006 Which side are you on? Identifying perspectives at the document and sentence levels. Proceedings of the 10th Conference on Natural Language Learning (CoNLL-X), pp. 109–116.
Marx, M. and A. Schuth
2010 DutchParl: The parliamentary documents in Dutch. Proceedings of the 7th Conference on Language Resources and Evaluation (LREC 2010), Malta.
Mullen, T. and R. Malouf
2006 A preliminary investigation into sentiment analysis of informal political discourse. Proceedings of the AAAI Symposium on Computational Approaches to Analysing Weblogs (AAAI-CAAW), pp. 159–162.
2008 The meaning of words: Obama versus McCain. Weblog, 12 October 2008 Available at wordwatchers.wordpress.com/2008/10/12/
Pennebaker, J.W., C.K. Chung, M. Ireland, A. Gonzales and R.J. Booth
2007a The Development and Psychometric Properties of LIWC2007. Available at www.liwc.net/LIWC2007LanguageManual.pdf
2007b Linguistic inquiry and word count (LIWC2007). Available at www.liwc.net
2009 Computational identification of ideology in text: A study of Canadian parliamentary debates. MSc paper, Department of Computer Science, University of Toronto, January 2009 Available at www.cs.toronto.edu/compling/publications.html
Thomas, M., B. Pang and L. Lee
Cited by other publications
Dallmann, Alexander, Florian Lemmerich, Daniel Zoller & Andreas Hotho
Dehghani, Mostafa, Hosein Azarbonyad, Jaap Kamps & Maarten Marx
Rheault, Ludovic & Christopher Cochrane
This list is based on CrossRef data as of 14 september 2019. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.