Philip A. Schrodt

Real Time, Time Series Forecasting of Inter- and Intra-State Political Conflict

We propose a framework for forecasting and analyzing regional and international conflicts. It generates forecasts that (1) are accurate but account for uncertainty, (2) are produced in (near) real time, (3) capture actors’ simultaneous behaviors, (4) incorporate prior beliefs, and (5) generate policy contingent forecasts. We combine the CAMEO event-coding framework with Markov-switching and Bayesian vector autoregression models to meet these goals. Our example produces a series of forecasts for material conflict between the Israelis and Palestinians for 2010. Our forecast is that the level of material conflict between these belligerents will increase in 2010, compared to 2009.

Precedents, Progress, and Prospects in Political Event Data

The past decade has seen a renaissance in the development of political event data sets. This has been due to at least three sets of factors. First, there have been technological changes that have reduced the cost of producing event data, including the availability of information on the Web, the development of specialized systems for automated coding, and the development of machine-assisted systems that reduce the cost of human coding. Second, event data have become much more elaborate than the original state-centric data sets such as WEIS and COPDAB, with a far greater emphasis on substate and nonstate actors, and in some data sets, the incorporation of geospatial information. Finally, there have been major institutional investments, such as support for a number of Uppsala and PRIO data sets, the DARPA ICEWS Asian and global data sets, and various political violence data sets from the US government. This article will first review the major new contributions, with a focus on those represented in this special issue, discuss some of the open problems in the existing data and finally discuss prospects for future development, including the enhanced use of open-source natural language processing tools, standardizing the coding taxonomies, and prospects for near-real-time coding systems.

Automated Coding of Political Event Data

Political event data have long been used in the quantitative study of international politics, dating back to the early efforts of Edward Azar’s COPDAB [1] andCharles McClelland’s WEIS [18] as well as a variety of more specialized efforts such as Leng’s BCOW [16]. By the late 1980s, the NSF-funded Data Development in International Relations project [20] had identified event data as the second most common form of data—behind the various Correlates of War data sets— used in quantitative studies. The 1990s saw the development of two practical automated event data coding systems, the NSF-funded KEDS (http://eventdata. psu.edu; [9, 31, 33]) and the proprietary VRA-Reader (http://vranet.com; [15, 27]) and in the 2000s, the development of two new political event coding ontologies— CAMEO [34] and IDEA[4,27]—designed for implementation in automated coding systems. A summary of the current status of political event projects, as well as detailed discussions of some of these, can be found in [10, 32].

Data-based Computational Approaches to Forecasting Political Violence

The challenge of terrorism dates back centuries if not millennia. Until recently, the basic approaches to analyzing terrorism—historical analogy and monitoring the contemporary words and deeds of potential perpetrators—have changed little: the Roman authorities warily observing the Zealots in first-century Jerusalem could have easily traded places with the Roman authorities combatting the Red Brigades in twentieth century Italy.

PETRARCH2: Another Event Coding Program

The PETRARCH2 coding program implements a new coding algorithm, based on a syntactic constituency parse, to extract who-did-what-to-whom political event data from structured news stories. Events are coded according to the CAMEO (Gerner et al. 2001) coding ontology. This software improves upon previous-generation coding software such as TABARI (Schrodt 2001) by using a deep syntactic parse rather than shallow parsing.