Ode to good news

Good news stories are hard to find these days. So Ode magazine, (“the online community for intelligent optimists”) has been forced to work harder to find articles with a positive spin. Its editor came up with the idea of an algorithm that could sense the tone of daily news and sort the uplifting stories from those of woe and despair.

The OdeWire system, dubbed a “slant engine”, has been recently released in beta testing, according to Scientific American. It can sort and aggregate news from the world’s 60 largest news sources based on solutions, not problems.

OdeWire is “the first automated optimistic, solutions-oriented 24/7 news source in the world”, says odemagazine.com. And this must be a good thing because “a more positive news diet supports your health and happiness in this challenging world”.

Web semantics developers have previously trained computers to classify news topics based on intuitive keywords and recognisable names. But the slant engine starts by classifying a story’s topic as either a world problem, such as disease or poverty, or a social good, like healthcare or education. Then it looks for revealing phrases: “efforts against” is likely to indicate something positive, while “setbacks” suggests a negative story. If words like “hydrogen” and “bomb” dominate a story, OdeWire gives it a black mark, but if “hydrogen” and “economy” are found in the same story, it is highlighted as an article about renewable energy sources. Plus, the system is designed to collect only “meaningfully optimistic” stories, discarding articles about subjects like sport and celebrities.

Slant identification could eventually specialise internet content for pockets of consumers, and make advertisements more engaging. By tracking attitudes in writing it could even help keep tabs on the relative liberal or conservative leanings of the media.