Posts Tagged ‘Twindex’

Election 2012: The Semantic Recap

There’s no such thing as too much post-election coverage, is there? Alright, maybe there is. But we couldn’t let things die down without at least a nod to those in our space that have delivered the semantic industry’s own take on the topic.

Here are a few you may want to review:

Twitris Election Insights:

“The Twitris system had an amazing night–while Nate Silver’s model might have received well deserved attention, Twitris gave better indications and insights and large majority of the polls,” wrote Dr. Amit Sheth, Kno.e.sis Ohio Center of Excellence in Knowledge-enabled Computing director and LexisNexis Ohio Eminent Scholar, in an email to us. The semantic social web application (first covered here) is a project of Kno.e.sis at Wright State University.

Read more

Twitter Provides More Information on API Direction — But Is It Enough?

Last week we reported here on the progress that Nova Spivack’s #OccupyTwitter petition was making in terms of attracting signatures, and on the petition’s request that Twitter clarify just what its intentions for the developer community are around its API. Many semantic and sentiment analysis applications, of course, depend heavily on the Twitter API.

Well, the end of last week saw a blog post from Michael Sippey of Twitter that provided some more information on the API issue. He wrote:

Read more

Picking the President: Twindex, Twitris Track Social Media Electorate

The U.S. is a mere three months away from choosing who will be its leader for the next four years. The semantic web is a supporting player in the action.

This week, of course, saw the debut of the Twitter Political Index (Twindex), a joint effort between Twitter, Topsy, and the Mellman Group and NorthStar Opinion Research polling groups. Since the Semantic Web Blog last spoke with Topsy execs here, the company has refined its sentiment analysis to the point where it could be released for the Twindex. The sentiment analytics engine ingests hundreds of millions of English-language tweets a day and computes sentiment for all terms in Twitter, though that’s not publicly available yet.

In its Twindex incarnation, Topsy aggregates the underlying sentiment score minute by minute, and then that is rolled up into an hourly and daily score for each candidate, says Rishab Aiyer Ghosh, co-founder and chief scientist at Topsy Labs. Behind the scenes, “that score is normalized so that it is on 0 to 100 scale comparing to all the other terms people talk about,” he says, which is important for keeping perspective on the candidates in context relative to whatever else may be on the mind of the collective social media conscience. It also is weighted to include the scores of the previous two days before its publication at the end of the day, and smoothed out so that it doesn’t jump around in helter-skelter fashion.

Read more