By the time a topic is 'trending' on Twitter, it's probably old news already. Today in New York City, data-crunching company Dataminr announced a new tool for journalists. Its goal is to seek out news stories before they're heavily reported.
Dataminr For News does this by scanning Twitter, albeit in a slightly different way from existing filter tools. The news-gathering tool was developed as a partnership with Twitter and CNN, whose reporters and editors have been using the software for six months and have helped shape it during that time.
According to Dataminr CEO Ted Bailey, Dataminr For News is different from tools such as Tweetdeck, Hootsuite, and Twitscoop because it's 'a tool for when you don't know what you're looking for.' Rather than filter Twitter-wide posts based on keywords - which would involve knowing specifics about an event before it occurred - the platform uses an algorithm that analyzes Tweets based on parameters such as geolocation and clustered reports.
It's also able to pinpoint whether real-time reports have been posted by 'citizen journalists' or traditional news outlets. This helps the newsroom jump on a developing story as a scoop rather than rehash already-reported stories.
Once Dataminr detects a noteworthy news event in the early stages of a Twitter trend, reporters and editors using the system can be alerted in a number of ways. There's a desktop client for Dataminr For News, as well as alert mechanisms that feed into email, mobile apps, and existing editorial systems. The system also seeks out and gathers related photos and videos that can be used to report events in near-real-time.
In recent months, CNN says that two stories per day have started out as Dataminr tips. Internally, the news-gathering system is known as CNN Tripwire. At the event, CNN executives stressed that Dataminr For News hasn't replaced traditional initial reporting and fact-checking; instead, it's more like a police scanner. After reporters are alerted to a breaking-news event via Dataminr, they still make phone calls and do the legwork to corroborate and flesh out the story.
Dataminr and CNN also report that the system has been a valuable source for feature stories. Features writers and editors can be alerted to building trends that aren't necessarily breaking news, but can be used to research and write longer-form pieces. Dataminr's Bailey says the technology isn't a 'one-size-fits-all product... every newsroom worker gets different types of alerts based on their role.'
Although pricing information wasn't announced at the Dataminr For News unveiling today, Dataminr's Bailey said that it will be a paid product. There will be an enterprise package for large customers similar to CNN, but also smaller implementations of the news-gathering platform.
No comments:
Post a Comment