While news reports are often seen as a rough draft to history, a new artificial intelligence engine may be able to use historical news information to figure out the future.

Computer and technology boffins, Eric Horvitz and Kira Radinsky are using two decades of New York Times’ stories and other resources to identify the underlying connections between real-world events and predict what will happen next.

They believe that the valuable data lies in the less dramatic stories and non-obvious trends that get overshadowed, for example, by riots and disease, and that by analysing these stories, as well as using real time data, they can find links and patterns in the news and therefore use this to predict the future.

In 1973 the New York Times published news of a drought in Bangladesh, and in 1974 it reported a cholera epidemic. Following reports of another drought in the same country in 1983, the newspaper again reported cholera deaths in 1984. Alerts about a downstream risk of cholera could have been issued nearly a year in advance.

Such observations could in this case help Bangladeshi water managers keep a closer eye on their treatment programmes, or for healthcare workers to be wary of an outbreak in the future.

When forecasting of disease, violence, and numbers of deaths, the system’s warnings were correct between 70 to 90 percent of the time.

While life continues to change, human nature stays the same and the environment remains consistent in reaction to humans and our ways. Mark Twain once said, “the past does not repeat itself, but it rhymes.”  So often we can be heard saying, “who knows what the future holds?”

Perhaps we do…

[Source: Smithsonian.com]