Browsing “Disqus” Clusters

We are experimenting with the new “Disqus” API in house. In this video, I show results from a 5-day query against the public API for the term Syria. The 50,000+ results are drawn from a variety of mass media discussion boards, including Al Jazeera, Fox News & CNN. When the results are de-duplicated and machine clustered, an interesting pattern of form-letter commenting is revealed. Further research is needed to see if this is spontaneous or coordinated. Either way, it is a novel parallel to mass e-mail campaigns.

About Stuart Shulman

Stuart Shulman is a political science professor, software inventor, entrepreneur, and garlic growing enthusiast who coaches U13 boys club soccer and in the Olympic Development Program with a national D-license. He is Founder & CEO of Texifter, LLC, Director of QDAP-UMass, and Editor Emeritus of the Journal of Information Technology & Politics. Stu is the proud owner of a Bernese/Shepherd named "Colbert" who is much better known as 'Bert. You can follow his exploits @stuartwshulman.
This entry was posted in API, DiscoverText, Disqus, product and tagged , , , , , , , , . Bookmark the permalink.
  • jonathan hegranes

    Love to see the many awesome ways that people are tapping into the @disqus API! This is one of the most powerful tools we have, and we just talked about this further with the release of “Disqus Labs” —

  • Pingback: Browsing “Disqus” Clusters | Computational and Data Journalism |

  • Tyler Hayes

    This is remarkable. We’ll be sharing this internally and it’s already put a smile on my face.

    • Stu Shulman

       Hey Tyler…this comment put a smile on my face! We should talk…~Stu

      • Tyler Hayes

        You bet. Feel free to shoot @hegranes:disqus  or me (or any of us) an email anytime.

        • Stu Shulman

           Joe Delfino will be reaching out to your team and I am visiting GNIP in Boulder next week. We have *lots* of ideas. It is particularly important, for example, that we be able to harvest “avon” while excluding non-exact matches, like “travon”. ~Stu

  • Rita Dawson

    I also heard about this discussion through Fox I suppose. The new Disqus API seems to work out well it seems. I think I should also try it. Anyways, thanks for sharing this informative post.