How to Identify Fourquare Influencers by Analysing Check-in Data

When people use Foursquare to check-in to a location they often leave a visible trail of their likes and interests that can be analyzed using Social Media Analytics, especially if the check-in is echoed on Twitter (many Foursquare and Twitter accounts are linked, providing public access to check-ins of the linked accounts).

Segmenting Foursquare check-in data is much easier than segmenting other social media data as check-in data contains context, has some structure and is short, and I was able to take about 30% of the close to 20 million check-ins over the last 3 months and put them into one category or another.  Here’s some examples using an approach I developed around Radian6′s capabilities to find influential individuals.

College Influencers:

  1. @BigBoi,536 Followers
  2. @tommytrc – – 122,872 Followers
  3. @steelers      - – 123,096 Followers

Restaurant / Dining out Influencers (turned out to be the same 3 people for Sports Influencers):

  1. @levarburton – 1,659,114 Followers
  2. @Agent_M       – – 1,408,664 Followers
  3. @AmyJoMartin - – 1,270,197 Followers

Museum Influencers:

  1. @CoryBooker -1,096,600 Followers
  2. @wallpapermag – – 473,589 Followers
  3. @RYOtheSKYWALKER – – 293,341 Followers

To learn more, see this post at or check out my Social Media Analytics book.

Twitter Digg Delicious Stumbleupon Technorati Facebook Email
blog comments powered by Disqus