SXSW Twitter Influence and Communities

The South by Southwest festival kicked off on 11th March 2016. During the course of the festival we will collect tweets relating to the event in order to gain insight into the influencers and communities on Twitter.

On the first day we collected approximately 150k Tweets.

We use a methodology which analyses the communications between users (Retweets, Mentions, Replies) and the way in which these communications form communities of users. From this structure we can discover:

  1. The most Influential Twitter users overall.
  2. The users who are connectors between different groups in the overall conversation.
  3. The communities and groups of users reflecting different topics of interest.

SXSW is now an event which attracts big name sponsors and big marketing budgets. Using conventional Twitter metrics like Retweets & hashtag usage the big names tend to drown out smaller but interesting stories which can be found on Twitter. This methodology is designed to overcome that problem and discover a more rounded picture of the event as reflected on Twitter.

Here is a link for further technical information about the methodology used for this analysis.

Top Performers on Day One

Here are the tables for performance on Twitter in four different ways. There is an explanation of each of the measures in the Appendix below.

Tables Explained

Top Overall — Most Influential Users

Influence is measured by combining the quantity of connections (retweets, mentions, replies), the quality of the connections of the user & the reach of the user’s tweets. This is adjusted for the number of followers a user has to correct for the disproportionate influence of users with very large numbers of followers.

Top Page Rank

Page Rank measures each node’s importance based on the importance of the nodes to which it is connected and the importance of the nodes to which they are connected and so on.

Top Connectors

The value of a user’s connectedness is measured using an algorithm called Betweenness Centrality. This measures how well a user is connected to all other users compared with everyone else.

Most ‘Interesting’ Users

Interestingness is measured by finding the users with the most importance when simply corrected for number of followers. This finds smaller users who made a relatively high impact.

Twitter Conversation Map

Here is the conversation map for Day One:

In this view the size of the nodes is based on the Page Rank measure.

By visualising the Twitter conversation in this way in this way it is possible to see the most influential users and how they are starting to congregate together into communities sharing a common interest.

Here is a view which sizes the Nodes by the most Connected.

The users who are best connected in the network are very different from the top Page Rank. The Overall and Page Rank tables are dominated by the big players. On the other had the Connectors and Interesting table throw up some less obvious but important stories.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.