A Quantitative Analysis of ‘Root Causes of Conflict’

  • Mihaela Bobeica
  • Jean-Paul Jéral
  • Teofilo Garcia
  • Clive Best
Part of the Integrated Series In Information Systems book series (ISIS, volume 18)

This chapter describes a method for the measurement of root causes of conflicts, as defined in a checklist drawn up by the European Commission’s External Relations Directorate General (DG RELEX) for monitoring and early warning. Our approach uses Latent Semantic Analysis to measure these conflict indicators on a corpus composed of news articles extracted from the archive of a media monitoring system, Europe Media Monitor (EMM), designed at the European Commission’s Joint Research Center (JRC). Latent Semantic Analysis is a statistical technique based on the analysis of the semantic similarity between words distributed across a corpus of documents. By taking a purely numerical approach to estimating these conflict indicators in news data, we have produced results that could be further used in foreign policy analysis and conflict assessment tasks and could provide timely alerts to policy-makers and analysts.


Singular Value Decomposition Semantic Similarity News Article Latent Semantic Analysis Semantic Space 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Austin, A. (2003). “Early Warning and The Field: A Cargo Cult Science?” Berghof Research Center for Constructive Conflict Management.Google Scholar
  2. Best, C.; van der Goot, Erik; de Paola, Monica; Garcia, Teofilo; & Horby, David (2002). “Europe Media Monitor - EMM.” JRC Technical Note No. I.02.88. http://press.jrc.it/NewsBrief/
  3. CarletonUniversity,CountryIndicatorsforForeignPolicy, http://www.carleton.ca/cifp/about.htm
  4. Carment, D. (2001). “Assessing Country Risk: Creating an Index of Severity,” Background Discussion Paper prepared for CIFP Risk Assessment Template, Carleton University.Google Scholar
  5. Coplin, W.D. and O'Leary, M, editors (1994). The Handbook of Country and Political Risk Analysis. 2nd ed., East Syracuse, NY: Political Risk Services.Google Scholar
  6. Delany C., Varga, S. (2002). Country Risk Assessment Report. Sub-Sahara Africa, Risk Assessments, Country Indicators for Foreign Policy, Carleton University. European Commission CheckList for Root Causes of Conflict, available at http://europa.eu.int/comm/external_relations/cpcm/cp/list.htm
  7. Fischer, M. and Wils, O. (2003). “Ploughing Through the Field: An Introduction to the PCIA Handbook Debate,” in A. Austin, M. Fischer and O. Wils (ed.), Peace and Conflict Impact Assessment. Critical Views on Theory and Practice, Berghof Handbook.Google Scholar
  8. Gerner, D. and Schrodt, Philip A. (1998). “The Effects of Media Coverage on Crisis Assessment and Early Warning in the Middle East,” in Schmeidl, Susanne; Adelman, Howard, Early Warning and Early Response. New York: Columbia International Affairs Online, 1998.Google Scholar
  9. Gotoh,Y. and Renals, S. (1997.) “Document Space Models Using Latent Semantic Analysis.” In Proc. Eurospeech, pages 1443-1446, Rhodes, 1997.Google Scholar
  10. Landauer T K, & Dumais, S T (1997) A Solution to Plato's Problem: The Latent Semantic Analysis Theory of the Acquisition, Induction, and Representation of Knowledge. Psychological Review, 104, 211-240.CrossRefGoogle Scholar
  11. Landauer T K, Foltz, P W, & Laham, D (1998) Introduction to Latent Semantic Analysis. Discourse Processes, 25, 259-284CrossRefGoogle Scholar
  12. Schmeidl S (2001) Early Warning and Integrated Response Development (Paper prepared for the Inter-regional Forum on Coping with Crises and Conflicts, Bucharest)Google Scholar
  13. Schmid A (1998) Thesaurus and glossary of early warning and conflict prevention terms, (abridgedversion).London,Fewer.Availableat: www.womenwarpeace.org/issues/prevention/docs/thes.pdf
  14. Schrodt, Philip A. and Deborah J. Gerner (2000). Analyzing International Event Data: A Handbook of Computer Based Techniques.Google Scholar
  15. Schrodt, Philip A., Shannon G. Davis and Judith L. Weddle (1994). “Political Science: KEDS - A Program for the Machine Coding of Event Data,” Social Science Computer Review 12,3: 561-588CrossRefGoogle Scholar
  16. Schrodt, Philip A. and Deborah J. Gerner (1994). “Validity Assessment of a Machine-Coded Event Data Set for the Middle East, 1982-1992,” American Journal of Political Science 38:825-854CrossRefGoogle Scholar
  17. University of Colorado at Boulder, “Latent Semantic Analysis @ CU Boulder,” available at http://lsa.colorado.edu
  18. University of Tennessee, Department of Computer Science, “General Text Parser,” available at http://www.cs.utk.edu/∼lsi/

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Mihaela Bobeica
    • 1
  • Jean-Paul Jéral
    • 2
  • Teofilo Garcia
    • 2
  • Clive Best
    • 2
  1. 1.University of Nice, CRDLFrance
  2. 2.European CommissionIPSC, Joint Research CentreItaly

Personalised recommendations