Change search
ReferencesLink to record
Permanent link

Direct link
Improving the selection of news reports for event coding using ensemble classification
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Peace and Conflict Research.
2015 (English)In: Research & Politics, ISSN 1078-0297, E-ISSN 2053-1680, Vol. 2, no 4Article in journal (Refereed) PublishedText
Abstract [en]

Manual coding of political events from news reports is extremely expensive and time-consuming, whereas completely automatic coding has limitations when it comes to the precision and granularity of the data collected. In this paper, we introduce an alternative strategy by establishing a semi-automatic pipeline, where an automatic classification system eliminates irrelevant source material before further coding is done by humans. Our pipeline relies on a high-performance supervised heterogeneous ensemble classifier working on extremely unbalanced training classes. Deployed to the Mass Mobilization on Autocracies database on protest, the system is able to reduce the number of source articles to be human-coded by more than half, while keeping over 90% of the relevant material.

Place, publisher, year, edition, pages
Sage Publications, 2015. Vol. 2, no 4
Keyword [en]
Protest, machine coding, SVM
National Category
Political Science (excluding Public Administration Studies and Globalization Studies)
Research subject
Political Science
URN: urn:nbn:se:uu:diva-269022DOI: 10.1177/2053168015615596OAI: diva2:881986
Available from: 2015-12-12 Created: 2015-12-12 Last updated: 2015-12-14Bibliographically approved

Open Access in DiVA

fulltext(645 kB)55 downloads
File information
File name FULLTEXT01.pdfFile size 645 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Croicu, Mihai
By organisation
Department of Peace and Conflict Research
In the same journal
Research & Politics
Political Science (excluding Public Administration Studies and Globalization Studies)

Search outside of DiVA

GoogleGoogle Scholar
Total: 55 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 199 hits
ReferencesLink to record
Permanent link

Direct link