Extracting Relevant Information from Big Data to Anticipate Forced Migration
- 1.2k Downloads
In this paper, we investigate how to extract the relevant information for forced migration from big data. Data-driven approaches have the potential to provide humanitarian agencies with real-time decision-making tools. However, very few humanitarian organisations have been able to gather, analyze and employ the data to its full potential due to capacity limitations.
This research is supported by the Social Sciences and Humanities Research Council of Canada (SSHRC) Partnership Development Grants (PDG) and the Natural Sciences and Engineering Research Council of Canada (NSERC) Collaborative Research and Training Experience Program (CREATE). We thank the anonymous reviewers for their through comments.
- 1.Wei Y, Taylor A, Yossinger NS, Swingewood E, Cronbaugh C, Quinn DR, Singh L, Martin SF, Berkowitz S, McGrath S. Using large-scale open source data to identify potential forced migration. In: Knowledge Discovery and Data Mining (KDD) 2014 Workshop on Data Science for Social Good; 2014. 4 pp.Google Scholar
- 2.Allan J, Ballesteros L, Callan JP, Croft WB, Lu Z. Recent experiments with inquery. In: Proceedings of the 4th Text Retrieval Conference; 1995. p. 49–64.Google Scholar
- 4.Hoffman M, Bach FR, Blei DM. Online learning for latent Dirichlet allocation. In: Advances in Neural Information Processing Systems; 2010. p. 856–64.Google Scholar
- 7.Robertson SE, Walker S, Jones S, Hancock-Beaulieu MM, Gatford M, et al. Okapi at TREC-3. In NIST Special Publication SP, vol. 109; 1995. p. 109.Google Scholar
- 8.Blei DM, Ng AY, Jordan MI. Latent Dirichlet allocation. J Mach Learn Res. 2003;3:993–1022.Google Scholar
- 10.Wang X, Grimson E. Spatial latent Dirichlet allocation. In: Adv Neural Inf Proces Syst. 2008;1577–84.Google Scholar