Journalism does add value!

Forecasting future wars

The ultimate example of the aphorism "Hindsight is 20:20" may be war.

Every armchair policy analyst who's ever read the front page of the New York Times knows, just knows, that those in power should have seen the latest crisis coming, whatever or wherever it may be.

But can you really predict grave conflicts simply by reading the newspaper? It may indeed be possible, but only if you can track many newspapers over time.

A Research Project by Devika Subramanian, professor of Computer Science at Rice University, Scours News Coverage for Patterns of Conflict. The module is true to computing norms based on patterns and looks to evict human biases in reporting.

An extract from a piece on this project depicts,

The program relies on dynamic Bayesian networks to extract events pertaining to interactions between countries from news reports (i.e., who did what to whom and when).

The computer learns the significance of certain words and phrases and calculates from their occurrence the probability that a news story is relevant.

It follows the "-10" and "+10" conflict/cooperation weighting familiar to political scientists for rating the severity of events. The computer is trained on a small collection of stories marked by a human as being relevant or not.

But then the one unanticipated challenge, according to the researcher, was the number of war metaphors that generously sprout out in sports reports!