Narrative Science is a company that launched out of a project at the Intelligent Information Lab at Northwestern University. They make a software platform called Quill which writes documents for you, based on raw data.
Whether describing your top sales performers or evaluating your portfolio against a benchmark, Quill identifies the facts that are foundational to your narrative. Since not every result from this data is interesting or important, Quill uses your business rules to identify thresholds, drivers, trends and relationships to determine what matters most to your business.
The software would presumably work best with data-loaded events which aren’t open to much interpretation, Some of their early work, for instance, was automatically writing summaries for baseball games. Baseball is an easily quantifiable sport which progress through an ordered time-scale. You can review the box score of a baseball game and reconstruct a fairly accurate history of what was happening—who was ahead, what major events occured in the game, etc.
What Narrative Science does is not write stories in advance, as much as it wrotes potential stories in advance. It identifies the ways in which stories might be written.
From an Atlantic article about the company:
When Narrative Science inks a deal with a new client, their writers begin work customizing the existing platform within a configuration layer. House style—how to format names and dates, when to italicize, and so on—is the easy part. What takes more time is establishing the facts and inferences that will conceivably be drawn from client data, as well as a “constellation” of possible story angles through which the data might be presented. In the case of baseball, this means “all the scenarios that might be derived from the raw data of a box score": the slugfest, the shutout, the pitcher’s duel, the back-and-forth, postponed by rain, on and on.
For their part, they claim this isn’t an effort to put writers out of work:
[...] while Narrative Science will certainly replace some types of human-generated writing, the stories they’re most excited about are the ones journalists rarely cover. Because of readership expectations, no journalist would write a story with relevance to only one person, or a few—sports writers, for instance, don’t write about Little League games in the first place. That’s why the company’s putting special effort into what they call “audience of one” applications—narratives that bring professional-caliber prose insight where right now we only have confusing data.
The author the Atlantic article notes the following:
As a journalist and fiction writer, it of course struck me to think about the relevance of all of this to what I do. I arrived at the Chicago office prepared to have my own biases confirmed—that the human mind is a sacred mystery, that our relationship to words is unique and profound, that no automaton could ever replicate the writerly experience. But speaking with Hammond, I realized how much of the writing process—what I tend to think of as unpredictable, even baffling—can be quantified and modeled.
There’s the key: “how much of the writing process...can be quantified and modeled.” The quantification and modeling of a human-centered process is the key to automation. This last passage has me wondering how much of lives and jobs we might find surprisingly quantifiable.