Mapping Violent Presence of Armed Actors in Colombia

Abstract

<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>

Land and State Capacity During Civil Wars: How Land-Based Coalitions Undermine Property Taxation in Colombia

“…The information used to code violent actors comes from Centro de Investigación y Educación Popular (CINEP), a prominent Jesuit research institution and human rights think tank in Colombia, which based on both national and local newspapers and an extensive network of grassroots organizations, collects and systematizes information about human rights violations and armed attacks on a daily basis. Information about the location, victim, perpetrator, and type of action is recorded in Noche y Niebla , one of CINEP’s main outlets, and geocoded by Osorio et al (2019).…”

Legacies of Resistance: Mobilization Against Organized Crime in Mexico

“…Eventus ID is a supervised coding protocol that relies on dictionaries of actors and toponyms to identify actors’ presence in specific locations as mentioned in news stories. A similar approach has been used to geo-locate the violent presence of armed actors elsewhere (Osorio et al, 2019). To build the actors dictionary, we relied on our knowledge of the autodefensas movement and complemented it with Named Entity Recognition software (The Stanford Natural Language Processing Group, 2014), which helped identify additional autodefensa groups.…”

One step ahead of the law: The net effect of anticipation and implementation of Colombia’s illegal crops substitution program

“…The later, are defined as killings during war actions. Also, to complement data on conflict, we have municipal data of FARC actions related to violation of human rights, coded by Osorio, Mohamed, Pavon, and Brewer-Osorio (2019), based on publications of narratives of conflict in Noche y Niebla (NN) magazine created by the non-governmental organization…”