An Automated Information Extraction Tool for International Conflict Data with Performance as Good as Human Coders: A Rare Events Evaluation Design

By Gary King, Will Lowe. International Organization, 2003

434 citations recorded by the source corpus.

Despite widespread recognition that aggregated summary statistics on international conflict and cooperation miss most of the complex interactions among nations, the vast majority of scholars continue to employ annual, quarterly, or (occasionally) monthly observations. Daily events data, coded from some of the huge volume of news stories produced by journalists, have not been used much for the past two decades. We offer some reason to change this practice, which we feel should lead to considerably increased use of these data. We address advances in event categorization schemes and software programs that automatically produce data by “reading” news stories without human coders. We design a method that makes it feasible, for the first time, to evaluate these programs when they are applied in areas with the particular characteristics of international conflict and cooperation data, namely event categories with highly unequal prevalences, and where rare events (such as highly conflictual actions) are of special interest. We use this rare events design to evaluate one existing program, and find it to be as good as trained human coders, but obviously far less expensive to use. For large-scale data collections, the program dominates human coding. Our new evaluative method should be of use in international relations, as well as more generally in the field of computational linguistics, for evaluating other automated information extraction tools. We believe that the data created by programs similar to the one we evaluated should see dramatically increased use in international relations research. To facilitate this process, we are releasing with this article data on 3.7 million international events, covering the entire world for the past decade.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/195ba4e60c5840de438aa5b22bd99aca33339ffd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Modeling relational events via latent classes (2010, methodology): “Figure 4: Proportion of assignments per week for latent classes from a data set of international political events [15], with typical senders, receivers, and action types shown in Table 1.”
War and the World Economy (2006, methodology): “We relied on the event data collection of King and Lowe (2003) for the three conflicts.”
Spinning gold: The financial returns to stakeholder engagement (2014, methodology): “While currently time intensive, progress in information extraction software development (King & Lowe, 2003) could allow for lowercost deployment in the near future.”
A Method of Automated Nonparametric Content Analysis for Social Science (2010, methodology): “Indeed, large-scale projects based solely on hand coding have stopped altogether in some fields (King and Lowe 2003, 618).”
POLITICAL CAPABILITIES, POLICY RISK, AND INTERNATIONAL INVESTMENT STRATEGY: EVIDENCE FROM THE GLOBAL ELECTRIC POWER GENERATION INDUSTRY † (2010, background): “Information extraction is a constrained form of natural language understanding in which only prespecified information is acquired from textual data’ (King and Lowe, 2003: 638).”
Can Large Language Models Transform Computational Social Science? (2023, background): “, 2019; Tufekci and Wilson, 2012), and international relations (King and Lowe, 2003).”
Not All Sparks Light a Fire: Stakeholder and Shareholder Reactions to Critical Events in Contested Markets (2017, methodology): “Cambridge, MA: Harvard University Press.”