SemTechBiz SF SemTechBiz UK SemTechBiz NYC more TVNewser TVSpy GalleyCat AppNewser UnBeige AgencySpy PRNewser 10,000 Words FishbowlNY FishbowlLA FishbowlDC MediaJobsDaily SocialTimes AllFacebook AllTwitter

Huffington Post Integrates OpenCalais

Jennifer Zaino
SemanticWeb.com Contributor

Online publisher The Huffington Post recently integrated the OpenCalais semantic web service from Thomson Reuters. Its initial adoption is for its local Chicago coverage, which it initiated during the election year; New York is next on the list. Plans are in place to leverage the technology with financial news and updates as well.

OpenCalais is saving the publisher a tremendous amount of time and work to use the API to identify appropriate entities, facts, and events to ensure that The Huffington Post editorial team is on target with tagging stories for local audiences.

“It allows us to go down to the hyperlocal level,” says Huffington Post CTO Paul Berry, providing users a targeted stream of stories regarding their local area. “It’s really wonderful for super-efficient metadata categorization, and then you can do interesting things once you have organized the data set.”

As an example, he notes that the technology can tag an entry as appropriate to Chicago local coverage even if Chicago isn’t mentioned anywhere in the story — perhaps just a museum or monument in the city is referenced.

“OpenCalais can pick up on that and suggest that this story is about Chicago,” he says. In combination with its content management system, with which it has integrated the technology, that’s the kind of help that makes its editors ever more efficient — which Berry says is a core mission at the company.

Human editors must remain an important part of the tagging mix, because you still need to ensure that suggestions aren’t too tangentially related to a locality to surface to online readers. For example, a story about Barack and Obama’s date night in Paris might mention that they flew there from New York, but the mention of New York in that instance wouldn’t necessarily be targeted enough to include that article as part of local New York coverage. That’s important for a good user experience and credibility with readership.


Semantic web technologies such as OpenCalais are coming along at the right time in the publishing industry, where things are tough and getting tougher.

It’s no longer a bonus for editors to be really efficient, Berry says: “Now it is a pre-requisite.” Without it, it could take a full-time person to go through all copy — The Huffington Post runs about 1,000 stories a day — to determine appropriate local content. With OpenCalais, it’s about five-minutes twice a day to categorize content automatically and then review the feedback for approval. “It’s organized and structured and you can trust its accuracy,” he says.

The use of the semantic web service on the site may not be overtly obvious to the readership, but Berry thinks it’s making a difference in that they’re noticing more how much they can drill into. So, for example, if they’re reading one story it’s easier to find other stories like that.

“That’s a key thing, to match up stories to where either the reader is from, or who the reader is friends with or what story it is related to,” he says. “That’s where we are taking semantic technologies.” The Huffington Post also is looking at other semantic technologies to help moderate its content; it has a minority investment in a startup called Adaptive Semantics Inc. that enables that.

The advertising piece just flows from there, as well, with OpenCalais’ ability to help identify stories for tagging tying into the revenue side of the publisher’s content management system. It will enhance its ability to leverage services such as Google AdSense for picking up context and delivering ads that are incredibly well-targeted across its site.

“That is super-critical for us,” he says. “It’s safe to say we are really excited about what happens this year.”

SemTechBiz is Less Than 2 Weeks Away

The Semantic Tech & Business Conference (SemTechBiz) is coming to San Francisco on June 3-7! Join us for case studies, innovative panels, tutorials, and keynotes that will provide you with practical advice, hands-on guidance, and breakthrough approaches to solving business problems with semantic technology. Passes go up $200 at the door. Sign up now and save !