The old adage that "one must learn from the past or else be condemned to repeat it" may turn out to be more prescient than astute today. Microsoft Research's Eric Horvitz and Technion-Israel Institute of Technology's Kira Radinsky have announced the creation of a new software system that they used to scan and analyze 22 years of New York Times articles prior to its connecting content to events that transpired years later.

"The system [is] able to 'learn' correlations between events by looking at sequences of stories in particular places," relayed The Verge's Adi Robertson. "[I]f an article was published about a drought in one place, for example, there was an 18 percent chance of a drought being reported there later. And both droughts and storms can lead to cholera outbreaks."

Though Robertson admits that this concept isn't exactly unique, the practicality of Horvitz's and Radinsky's entry into the realm of systematic prognostication could be employed to determine the timing of forthcoming disasters/crises affecting millions. Potentially detectable patterns in history, if one were to be so audacious, might be able to help the software detect earthquakes or, as Robertson suggests, a mine collapse.

In addition to the New York Times, Horvitz's and Radinsky's system has also set its computer sights on archives culled from nearly 100 Web sources such as Wikipedia.

If what the duo is doing sounds too close to the irrational stuff of sci-fi, consider that there's already similar systems available for use such as Recorded Future - "The Best Intelligence Analysis Tool for Open Web Sources."

CNN's Laura Hazard adds that information garnered from Twitter and Google has been utilized in the past to track flu epidemics.

The components of the system that make it at least somewhat viable in the mind of Hazard include its abilities to:

-          "learn" from patterns and data

-          remain, as software rather than a human being limited by natural needs, "tireless" in study

-          have a lack of bias by merely processing data mathematically as opposed to consciously/unconsciously parsing with a human's innate tendency for subjectivity

-          access far vaster sources of information than its human counterpart imprisoned in a material realm of mediation by libraries, microfilm, computer consoles, etc.

"Eventually," Horvitz told the MIT Technology Review, "this kind of work will start to have an influence on how things go for people."

Follow @profklickberg