One of the rules of thumb taught in many communications courses is ‘know your audience’. It can also be useful to know what your audience thinks of you.

For example, what interests a random sample of the followers of the @BBCCollege Twitter account?

Over the past couple of years I have been experimenting with the idea of 'social interest positioning' - a technique for mapping the social interests of audiences around a particular person, tag, search term or shared link.

First, we need to sample an appropriate audience. For a person this might be some or all of their followers; for a hashtag, search term or shared link, it may be people recently using that tag, or term, or sharing, liking or bookmarking that link.

Having sampled our audience, we can then start to map out their interests by seeing who they follow. So, for each member of the audience sample, we grab the list of people they follow and construct a network diagram:

We can then see who is followed by a significant proportion of the audience sample, removing those who aren't commonly followed by the audience:

This leaves us with a much smaller, and more easily managed, network. We now need to associate these commonly followed accounts with particular interests in order to build a picture of what the audience in general is particularly interested in.

The map is constructed as a network visualisation, with lines going from audience members to the people they follow.

One tool I often use is Gephi, a cross-platform desktop application. For Excel users on Windows, NodeXL does a similar (those less beautiful!) job.

The visualisation is laid out as a map using a technique called a force-directed layout. This imagines links between people exerting an attractive force between them, with the result that it tries to position people who are followed by the same audience members close to each other. To the extent that by following a person they reflect your interests, people who are positioned close to each other can be seen as reflecting the common interests of their followers.

Sometimes there may be tensions - for example, when a person is notable or of interest for two or more reasons. So a ministerial MP may be followed both by constituents who follow local businesses and people interested in the ministerial matters that the MP is concerned with. In Communities and Connections: Social Interest Mapping, I describe how the followers of a Milton Keynes community action group appear to split into interest groups relating to charitable concerns on the one hand and social enterprise in the Milton Keynes area on the other.

We can use the resulting social interest maps to both identify the perceived concerns of a particular user or hashtag based on the common interests of their audience and to segment that audience into groups with slightly different interests.

We can also look at the interests of a particular user account by grabbing the set of people followed by that user and seeing how they connect. If we try to position these friends so that they are close to each other if they follow each other, we can generate a map of the shared interests of those friends. It’s a bit like a cocktail party where birds of a feather flock together even if they are all known by the host or hostess.

An example of this is seen in Visualising How @skynews' Twitter Friends Connect. It shows how people followed by @skynews tend to follow each other, revealing a certain amount of structure in that network, including MPs, political journalists and Sky journalists:

Although Twitter is currently one of the easiest social networks to get access to social data from, it is also possible to extract this kind of friendship connections data from other social networks such as Google+. The image below shows a fragment of the Google+ network around Red Bull Racing:

If you would like to experiment with visualising some social network data, please visit Visualising Twitter Friend Connections Using Gephi: An Example Using the @WiredUK Friends Network which provides a linked-to data set and mini-tutorial on how to start visually analysing using Gephi.

Comments

This entry is now closed for comments.

  • Comment number 6. Posted by Cherise W

    on 28 Sept 2013 11:09

    This does look somewhat complicated but I can definitely see the value going forward of determining 'kingpins' of social media. I think for media companies to be successful in the future, they will need to understand who these people are and how the process and disseminate information - I image the equation will get quite complex considering the number of categories and influence levels that need to be considered in this type of initiative.

    • This entry is now closed for comments. Number of positive ratings for comment 6: 0
    • This entry is now closed for comments. Number of negative ratings for comment 6: 0
    Loading…
  • Comment number 5. Posted by Olga Rikova

    on 24 Aug 2013 10:25

    Intriguing article Tony - thanks. I have to say I'm somewhat of an old-school journalist myself but it seems even wartime coverage is increasingly dependent on social media these days (considering the technology that sparked off the likes of the Arab Spring). I came across an interesting article on Big Data - http://www.wonkie.com/2013/08/12/using-big-data/ which got me thinking about the value of understanding social connections in so far as it will contribute towards determining relevancy and credibility of news information from social media applications.

    From your article, I'm quite surprised at how far the social mapping science has developed already - I can only imagine the impact it will have over the next few years as technology to post through social media becomes ubiquitous. Interesting times for journalists ahead!

    • This entry is now closed for comments. Number of positive ratings for comment 5: 0
    • This entry is now closed for comments. Number of negative ratings for comment 5: 0
    Loading…
  • Comment number 4. Posted by Meryl Coach

    on 8 Apr 2013 20:22

    Tony, I would be interested to find out how to use this mapping to figure out who the 'kingpins' of social media are within various niches. I've used Gephi and it's quite fascinating what inferences you can produce from the tool... given the growing trend towards convergence: http://newsgame.co.uk/52/convergence-and-journalism/ we were doing a social mapping exercise to see if we could determine who the key influencers were in terms of citizenship journalism. Curious if you've done any research in that space?

    • This entry is now closed for comments. Number of positive ratings for comment 4: 1
    • This entry is now closed for comments. Number of negative ratings for comment 4: 0
    Loading…
  • Comment number 3. Posted by Joseph Reddy

    on 9 Nov 2012 22:05

    Have to say it just looks very, very confusing to me!

    • This entry is now closed for comments. Number of positive ratings for comment 3: 0
    • This entry is now closed for comments. Number of negative ratings for comment 3: 0
    Loading…
  • Comment number 2. Posted by Anna Sempe

    on 3 Nov 2012 22:26

    @Craig Smith - agree with you about the (lack of) usefulness of this kind of social map for making inferences simply based on relationships between individuals. I do believe however that one can draw some really valuable inductive conclusions between individuals and 'causes' and 'common interest' groups (not everything on the social map that Tony is talking about at the individual level - they could just as easily be links between a person an an NGO representing a cause) - in that case the kind of demographic data about a cause's supporters could well lead to a better understanding of one's customers.

    • This entry is now closed for comments. Number of positive ratings for comment 2: 2
    • This entry is now closed for comments. Number of negative ratings for comment 2: 0
    Loading…
  • Comment number 1. Posted by Craig Smith

    on 2 Nov 2012 20:52

    Tony, some fascinating tools - have not come across either Gephi or NodeXL before. I think that these tools would be well-suited to commercial applications (especially with people trying to leverage social media data by finding the 'key influencers' in the market) - in terms of news applications though I'm not so sure. I have come across a few articles about using facebook in newsrooms - e.g. http://sizwemahlala.blogspot.com/2012/03/using-facebook-for-breaking-news.html - am curious to see how easy it would be to extrapolate the interests of individuals in a network merely by their associations - I can see it happening on the highest levels but not sure what real value that info would have for broadcasters.

    In terms of disseminating information it's a different matter altogether. Knowing how connected an individual is within a network is definitely invaluable. Consider the power such information can have in the context of the US elections for example - critiques of either candidate in articles like http://newsview.co.za/us-elections-2012/ or other notifications about the process itself could be distributed to key individuals who could facilitate the message going viral (supposing it's interesting or topical enough!). The same applies to commercial applications like distributing marketing messages. Collecting information inductively through a view of the network is much more difficult.

    • This entry is now closed for comments. Number of positive ratings for comment 1: 4
    • This entry is now closed for comments. Number of negative ratings for comment 1: 0
    Loading…

More Posts

Previous