Lost in Space: Geolocation in Event Data

Lee, Sophie J.; Liu, Howard; Ward, Michael D.

doi:10.1017/psrm.2018.23

Cited by 24 publications

(26 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, scholars tend to rely on secondary sources such as news reports, which are neither comprehensive nor unbiased. Moreover, while temporal disaggregation has been relatively successful (there is generally little ambiguity about the timing of an attack or a speech), pinpointing the location of that event has proved to be much more challenging and error-prone (Weidmann [62]; Lee, Liu, and Ward [32]). Machine coding also still cannot analyze sentences with a complex structure, and typically ignores the connection between them.…”

Section: Econometric Approachesmentioning

confidence: 99%

Conflict forecasting and its limits

Chadefaux

2017

View full text Add to dashboard Cite

Research on international conflict has mostly focused on explaining events such as the onset or termination of wars, rather than on trying to predict them. Recently, however, forecasts of political phenomena have received growing attention. Predictions of violent events, in particular, have been increasingly accurate using various methods ranging from expert knowledge to quantitative methods and formal modeling. Yet, we know little about the limits of these approaches, even though information about these limits has critical implications for both future research and policy-making. In particular, are our predictive inaccuracies due to limitations of our models, data, or assumptions, in which case improvements should occur incrementally. Or are there aspects of conflicts that will always remain fundamentally unpredictable? After reviewing some of the current approaches to forecasting conflict, I suggest avenues of research that could disentangle the causes of our current predictive failures.

show abstract

Section: Econometric Approachesmentioning

confidence: 99%

Conflict forecasting and its limits

Chadefaux

2017

View full text Add to dashboard Cite

show abstract

“…While there are many potential reasons for this non-finding, one is that the country-year level of analysis obscures any relationship. Following Marineau et al (2018), future research might disaggregate the analysis spatially, perhaps with event-level geocoding (Lee et al, 2018;Gunasekaran et al, 2018). With firm and group level data, one promising approach is to model interactions using sequence analysis methods (Casper and Wilson, 2015;D'Orazio and Yonamine, 2015).…”

Section: Resultsmentioning

confidence: 99%

Multinational Corporations and Political Violence: Trends and Forecasts

Akporiaye¹,

D’Orazio²,

Peinhardt³

2020

Preprint

View full text Add to dashboard Cite

Multinational corporations (MNCs) increasingly worry about the threat of targeted violence, particularly in the form of terrorist attacks. Why do terrorists target MNCs and which factors are sufficiently predictive to matter to decision makers? We identify potential theoretical explanations from the literature on MNCs and transnational terrorism. Then, using conflict forecasting methods, we show the best predictors are whether a country experienced attacks before, and whether such attacks are common in the region. In addition, exogenous factors such as income improve performance, but many of the typical explanations for transnational terrorism, such as those involving regime type, do not help to identify MNC targets. Furthermore, despite using multiple behavioral and economic measures of MNC activity, it does not appear that their actions have much of an impact on whether MNCs are targeted. Future research on corporate targets of political violence would benefit from analysis at the firm and group level.

show abstract

“…In this way, the software geo-references actors at the subnational level. A common challenge in event coding relates to correctly identifying the place of occurrence of an event (Lee et al, 2016, Chalabi, 2014. To address the geographic disambiguation challenge, Eventus ID uses a locations filter to eliminate matches that might look as toponyms, but do not actually refer to locations.…”

Section: Computerized Textual Annotationmentioning

confidence: 99%

Mapping Violent Presence of Armed Actors in Colombia

Osorio

Mohamed

Pavon

et al. 2019

Adv. Cartogr. GIScience Int. Cartogr. Assoc.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> Heat maps and Early Warning Systems have traditionally contributed to identifying and managing risks associated with crime trends, health hazards, and natural disasters. However, their application to analyzing civil war dynamics still is at an early stage. To address this need, this research integrates Natural Language Processing (NLP) tools and Geographic Information Systems (GIS) to generate an interactive map of the violent presence of armed actors in the Colombian civil war between 1988 and 2017. The NLP component generates fine-grained geo-location data of armed actors' violent presence. The GIS component then uses the geo-referenced data to present dynamic clusters of four main types of actors: Government forces, Insurgent organizations, Paramilitary groups, and Criminal organizations. Each type of actors is further disaggregated into a multitude of specific armed organizations. Based on anomalies in the spatio-temporal trends identified in the data, we develop an EWS methodology to detect “emerging”, “intense”, and “critical” cases. This application contributes to the efforts of the academic and policy communities to understanding the spatio-temporal dynamics of political violence and promoting sustainable peace in civil war settings.</p>

show abstract

Lost in Space: Geolocation in Event Data

Cited by 24 publications

References 15 publications

Conflict forecasting and its limits

Conflict forecasting and its limits

Multinational Corporations and Political Violence: Trends and Forecasts

Mapping Violent Presence of Armed Actors in Colombia

Contact Info

Product

Resources

About