Big news today. After many months of development The Weather Channel launches The Weather Channel Social, an integration of local, weather-related Tweets across The Weather Channel television, Web and mobile platforms. Wiredset’s Trendrr social curation and conversation analysis technology made this unique integration possible.
We’re proud to have worked with Twitter and The Weather Channel to launch one of the most ambitous natural language curation projects to date. The Trendrr Blog has a great overview of technical challenges of the project and how the team leveraged our proprietary technology to provide the solution.
We believe that this launch is an an important step in the evolution of tightly coupled social TV. And to put this into context Wiredset’s CEO Mark Ghuneim makes the following observations:
Informing news via real-time social intelligence is a powerful shift (one that remains in its infancy).
Clearly, news programs are integrating social networking in broadcasts as a platform for viewer interaction, but news agencies are just beginning to tap into social intelligence as a means to drive real time reporting and listening. The Weather Channel takes listening and reporting to an entirely new level by leveraging the social channel and participation of its audience in real-time to achieve:
- Compelling integrated social user experience
- Better on the ground reporting
- Real-time (web/apps/on-air) updates
- Improve SEO (by having real-time changing content and context)
- Unlocking the value of the Twitter fire hose
For news media the challenge is how to handle the volume and velocity and turn noise to a signal and context that makes Twitter in this case actionable.
With The Weather Channel’s initiative, we see social data evolve into an actionable state. This goes beyond art-project or colorful data visualization. In this case, social streams become a utility and an important new programming layer—something other TV networks can learn from.
Social data is becoming increasingly contextual and useful, evolving from a mass of user outreach to a more effective communicative medium, adding an important news-programming layer. We expect all news to be informed by its audience in some manner over the next few years. We have already seen integration into political coverage (think Obama’s Twitter campaign re: the debt ceiling vote) and one-off events (that guy in Abbottabad who inadvertently live-tweeted the bin Laden mission), but now we are seeing the next generation of data as content that informs broadcasts in real time to enrich the user experience across devices.
The Wall Street Journal highlights that “the online-messaging service on Thursday will begin to give TWC access to users’ tweets about local weather, according to the companies. TWC will showcase local-weather tweets both on its cable television channel and on www.weather.com and its iPhone mobile application, giving viewers “real-time,” or live, insights into weather events in their city or region.”
GigaOM highlights more of the technical challenges of the project:
“One of the biggest challenges of the integration was apparently to separate weather-related tweets from observations about all the other things that can be hot, cool and foggy in this world. The Weather Channel is relying on technology provided by the New York-based real time data specialists from Wiredset, which also runs Trendrr.com, to curate the Twitter firehose. Wiredset built an AI engine based on the Maximum Entropy Method of data analysis to make sense of all these tweets. Another challenge was that only three percent of tweets come with location information, which is why The Weather Channel is relying on Twitter profiles and location information within the actual text of each tweet, rather than geotagged data.
Did you know that Weather is already one of the most popular topics on Twitter:
● On an average day, U.S. users send approximately 200 weather-related Tweets per minute
● On an active weather day, U.S. users send between 300 to500 weather-related Tweets per minute
● Significant weather events can generate more than two million Tweets per day
