Article contents
Lost in Space: Geolocation in Event Data
Published online by Cambridge University Press: 06 July 2018
Abstract
Improving geolocation accuracy in text data has long been a goal of automated text processing. We depart from the conventional method and introduce a two-stage supervised machine-learning algorithm that evaluates each location mention to be either correct or incorrect. We extract contextual information from texts, i.e., N-gram patterns for location words, mention frequency, and the context of sentences containing location words. We then estimate model parameters using a training data set and use this model to predict whether a location word in the test data set accurately represents the location of an event. We demonstrate these steps by constructing customized geolocation event data at the subnational level using news articles collected from around the world. The results show that the proposed algorithm outperforms existing geocoders even in a case added post hoc to test the generality of the developed algorithm.
- Type
- Original Articles
- Information
- Copyright
- © The European Political Science Association 2018
Footnotes
Sophie J. Lee, Ph.D. Department of Political Science, Duke University, 140 Science Drive, Durham, North Carolina 27708, USA (sophie.jiseon.lee@gmail.com). Howard Liu, Ph.D. Candidate, Department of Political Science, Duke University, 140 Science Drive, Durham, North Carolina 27708, USA (haoliu.howard@gmail.com). Michael D. Ward, Professor of Political Science, Department of Political Science, Duke University, 140 Science Drive, Durham, North Carolina 27708, USA (michael.don.ward@gmail.com). The authors would like to thank John Beieler, Patrick Brandt, Andrew B. Hall, Andrew Halterman, Jan H. Pierskalla, and Philip A. Schrodt, as well as members of Wardlab for their insights and comments on this project. The editors and reviewers of this journal provided helpful suggestions. M.W. acknowledges support from National Science Foundation (NSF) Award 1259266. To view supplementary material for this article, please visit https://doi.org/10.1017/psrm.2018.23
References
REFERENCES
- 8
- Cited by