Science: Breathing Down Your Narrative
One reason that writers might want to be sure to credit each other for their work — in tweets, on Facebook, in their own posts and stories — is that there are alternatives not just in the pipeline but on the pages and Web sites of some news outlets near you.
Narrative Science fields a remarkably effective system, led by chief scientist Kris Hammond’s team, for turning data into highly readable copy. Sports stories, for example, have been found to follow such predictable patterns that scores can be fed in to the right algorithmic structure and turned around by the system as surprisingly convincing sports-news stories.
I’ve seen this work myself, and I can tell you it’s pretty remarkable.
Just days ago at the MIT Technology Review in Robot Journalist Finds New Work On Wall Street, Tom Simonite wrote up the software called Quill — an ironic name for something in a galaxy far, far away from a bird’s feather used as a pen.
Quill, Simonite writes, is a creature of Narrative Science in Chicago, set up in 2010 “to commercialize technology developed at Northwestern University that turns numerical data into a written story.”
Quill, Simonite tells us, has graduated from mostly sports writing to financial settings:
Narrative Science is now renting out Quill’s writing skills to financial customers such as T. Rowe Price, Credit Suisse, and USAA. One of its main tasks is to write up in-depth, lengthy reports on the performance of mutual funds that are then distributed to investors or regulators.
We hear from the Narrative Science CEO, Stuart Frankel, in the piece — which we must assume was, actually, written by Simonite and not by Quill (!):
Quill’s early career success generated headlines of its own, and the software was seen by some as evidence that intelligent software might displace human workers. Narrative Science CEO Stuart Frankel says that the publicity, even if some of it was negative, was a blessing.
“A lot of people felt threatened by what we were doing, and we got a lot of coverage,” he says. “It led to a lot of inquiries from all different industries and to the evolution to a different business.”
Before you apply for that MBA in artificial intelligence applications for financial writing, do realize that the Narrative Science context is always one of numbers, data.
A cousin to the kind of “natural language processing” (NLP) that Boston’s Trajectory is using in creating new potential discoverability for books — our story on that one is here — Narrative Science is using “natural language generation.” And the “natural language” being “generated” is rooted in data: scores and stats for sports writing, trading figures and factors for financial writing.
Still, as Simonite tells us:
Companies can tune Quill’s style and use of language based on what they need it to write. It can accentuate the positive in marketing copy, or go for exhaustive detail in a regulatory filing, for example.
Quill can also take an “angle” for a piece of writing. When writing about sports for an audience likely to favor a particular team, for instance, Quill can write a story that softens the blow of a loss.
Creeped out? Good. That’s right where I want you. Because surely by now you can see a new, digital reason to get some credit for other writers into your daily romps on various social media.
It tweets for thee, so credit others as you would have them credit you.
There’s more: Read the full story at Thought Catalog
Originally published by Thought Catalog at www.ThoughtCatalog.com