Share

Related Links

Top 5 Stories

News

Real-time data mining comes to Twitter

10 April 2012

Twitter is usually described as a micro-blogging social network. To many who monitor its ‘trending topics’ it is also an early warning news service, frequently pointing users to breaking news before the traditional news media reports it.

This ability for Twitter to be ahead of the news game was ably demonstrated by Dataminr and Bin Laden – the company told its clients about Bin Laden’s death before it broke over the traditional news services. According to a report in Ars Technica, “‘Dataminr sent an alert in this instance at 10:20 [p.m. Eastern time on May 1, 2011], based on only 19 messages,’ Dataminr founder and CEO Ted Bailey told the Twitter Devnest crowd. ‘This was, for our clients, the earliest warning system in the entire financial industry for this event, which had a dramatic effect on the market once it hit the financial radar.’” This was four minutes before Keith Urbahn, former chief of staff to former defense secretary Donald Rumsfeld, tweeted, “So I'm told by a reputable person they have killed Osama Bin Laden. Hot damn.” 

Dataminr has now been granted coveted access to Twitter’s Firehouse – the full feed of all tweets, unlimited. “We leverage Twitter and other social media data-sets,” says the company’s website, “as a global sensor network for detecting emerging events and public trends. Our clients include buy-side and sell-side firms in the finance industry as well as municipal and federal agencies in the government sector.”

Dataminr brings big data analytics to the world’s largest source of breaking news. It analyzes all 340 million daily tweets, discovering and reporting what it calls ‘actionable signals’, providing an early warning system for its clients.

But Dataminr isn’t just another social media analytics company; it brings big data analytics to standard social network analyses. Apart from analyzing the tweets themselves, “Dataminr takes the unique approach of merging Tweets with third-party and client proprietary data to perform multi-variable event detection,” it claims in its announcement. The result is the ability to map breaking world events to corporate interests in real time; an ability that will undoubtedly interest all large organizations, from international finance to multinational corporations, from national security and law enforcement agencies to the traditional news services themselves – and infosec at large.

This article is featured in:
Industry News  •  Internet and Network Security  •  IT Forensics

 

Comment on this article

You must be registered and logged in to leave a comment about this article.

We use cookies to operate this website and to improve its usability. Full details of what cookies are, why we use them and how you can manage them can be found by reading our Privacy & Cookies page. Please note that by using this site you are consenting to the use of cookies. ×