A network analysis of comedians who played the Edinburgh Fringe

William Wagstaff • 19 August 2021

Or why Dara O'Briain is the centre of the comedy universe

The Edinburgh Fringe is one of the world's largest arts festivals, open to anyone with any type of performance allowed. It is, however, best known for its comedy. 

To celebrate the 2021 Fringe festival, we looked at stand-ups from the previous Fringe to see how they are connected to one another through their followers on Twitter. 

To do this we used a technique called network analysis. Put simply, network analysis is the graphical representation of the relationships between variables (known as nodes). In this case our nodes are comedians who performed at the last Edinburgh Fringe but nodes could be brands, services, people, words or anything where you're interested in how it relates to something else.

For our Fringe analysis we used network analysis to identify clusters of comedians who share the same followers, the comparative size of their networks, which comedians are important in driving followers to others and who are the most influential in their networks.

We consulted the British Comedy Guide to create a list of comedians who performed at the 2019 Fringe festival and then collected their Twitter followers. 

We then created a network between comedians where each node represents a comedian and the node size represents the number of connections to other comedians.  You can see this in the graph below. 

In the graph,  connecting lines, known as edges, represent comedians sharing at least 50% of followers with a minimum threshold of 10,000 shared followers. 
my plot


It is known that people who share connections on social media tend to form clusters or communities. The network analysis shows that there are four main communities with each one defined by a different colour. Within each there is a larger node connected with smaller nodes. If you hover your mouse over the nodes it will display the name of the comedian and the number of degrees (or links) with other comedians.


Dara O'Briain has the most connections and therefore the largest node. Dara also performs very highly on what are known as network centrality measures. These are important because they identify the biggest influencers in the network. O'Briain has the highest degree centrality measure. This is a measure of the number of connections a node has. Important nodes have more connections and none are more important than Dara O'Briain.


It is not just how many connections a node has that's important,  it's also the importance of the nodes that it is connected to. A value known as Eigenvector centrality measures this. It decides the importance of a node by measuring how many other important nodes it is connected to.


The third measure we look at is known as betweeness centrality. This quantifies how many times a particular node comes in the shortest chosen path between two other nodes. The nodes with high betweenness centrality play a significant role in the communication and information flow within the network and can have a strategic control and influence over others. A good illustration of this is Lucy Porter in the yellow community (which we label Millican Izzard). The shortest path between Eddy Izzard and Sarah Millican goes through Lucy Porter so although she does not have the most connections, she has a strong influence in the network.


Let's now have a look at the four communities in more detail. We look at who is in them and what connects them, who has the most connections (known as degrees) in the group and who has the most influence as measured by their betweeness centrality and Eigenvector centrality score. 


We also look at what differentiates each community by identifying the top 5 Twitter users that are unique to that community. These are Twitter users that appear in this community but not in any of the other communities.


The largest community centres around Dara O'Briain. Present in every edge and connected to every other person in the community and many outside of it, Dara O'Briain is central to this Edinburgh Fringe based network. This is largely down to him being the host of the long running panel show Mock The Week, where he comes into contact with a lot of comedians. This community also contains a number of Irish comedic links - Neil Delamere, Alison Spittle, Andrew Maxwell, Eleanor Tiernan, Ed Byrne and Jason Byrne.


What differentiates this cluster from the others? The top five unique users followed on Twitter by those involved in this community are Brian O’Driscoll (former Irish rugby union player), RTÉ News (Irish and International News) , Des Bishop (Irish-American stand-up comedian), thejournal.ie (online Irish newspaper) and Amy Huberman (Irish actress and writer).


The presence of Irish celebrities is not surprising given the large number of Irish comedians within the community. It is not until you get down to the 14th most unique user, Milton Jones, that you get a suggestion of a link with Mock The Week. That Mock The Week is not a differentiator is to be expected. It is a show closely connected to a large number of comedians and has a large number of followers in all the other communities.


It is also notable that there are two news sources in the top five most unique users, which suggests that Irish news and current affairs has an important differential for this community.



The second biggest community is shown in blue. Present in all but one edge, Nish Kumar is central to the community and linked with the most people in it. In fact, many people in the group can be linked to Nish Kumar through appearing on shows that he has been a big part of: Ivo Graham, Sarah Kendall, Phil Wang, Desiree Burch and Sophie Duker have appeared on the News Quiz, a radio programme that Kumar hosted. Ed Gamble, Lou Sanders, Sarah Kendall and Phil Wang have been long term contestants on Taskmaster alongside Kumar and Desiree Burch has been on The Mash Report, a satirical comedy news series hosted by him. Josh Widdicombe links the rest of the comedians in the community. He was a regular on Stand Up For The Week with Seann Walsh, starred in Hypothetical and The Last Leg in which Maisie Adams has appeared and has been a host on Fighting Talk, a radio programme that Ivo Graham has featured on.


In relation to differentiation, the top five unique users followed by members of this community are Lolly Adefope (comedian), Michaela Coel (actor),  Akala (rapper), Sarah Pascoe (comedian) and Owen Jones (political commentator and columnist).


Taskmaster contestants Lolly Adefope and Sara Pascoe provide evidence that the show may be an important influence in this community, while Owen Jones suggest that left of centre politics may also be important. Akala has also been vocal about political issues on several occasions. He was a big supporter of Jeremy Corbyn and signed a letter (along with other musicians) declaring support for Corbyn in the 2019 election. The top ten most unique users also includes Sadiq Khan, Jeremy Corbyn, Alexandria Ocasio-Cortez and Ed Miliband. This political influence could be related to tv show The Mash Report which has in the past aired segments critical of Brexit and the alt-right.




The third community, shown in yellow, contains two main nodes: Sarah Millican and Eddie Izzard. In this community, members are linked by appearing on the same shows. Members have made appearances on Live at the Apollo, with each person apart from Tony Law, appearing in the show at least once. Sarah Millican, Lucy Porter and  Zoe Lyons were featured in a Live at the Apollo special, All Girls Live At The Apollo, highlighting women in comedy with Zoe Lyons also featuring in Pride Specials with Eddie Izzard hosting.


The top five unique users followed by members of this community are Sarah Brown (Chair of charity Theirworld and Executive Chair of Global Business Coalition for Education), 10 Downing Street (Office of the Prime Minister), Sarah Silverman (comedian), Sue Perkins (comedian and presenter) and Jennifer Saunders (actor, comedian and screenwriter).


Sarah Millican has appeared on Sarah Brown's podcast, 'Better Angels with Sarah Brown' and alongside ex PM Gordon Brown. Sarah  has also met with Eddie Izzard in Downing Street after Izzard completed 43 marathons for Sport Relief. The other three in the top five most unique users are all female comedian or comic actors which follows in terms of the All Girls Live At The Apollo link. The 7th most unique user in this community is Matt Lucas who, like Sue Perkins, has been a presenter on the Great British Bake Off.





The last of the four main communities, shown in green, is centred around Jon Richardson. He has been in shows heavily featuring the other two people in the group. He starred in Meet the Richardsons with his wife, Lucy Beaumont and captained his 8 out of 10 Cats Does Countdown team where Nick Helm has been a guest several times.


The top five unique users followed by members of this community are Danny Dyer (actor), Ant and Dec (presenters), Joe Wilkinson (comedian), Keith Lemon (comedian, actor, presenter) and Michelle Keegan (actor).  While Joe Wilkinson has been a regularly appearing as Rachel Riley's assistant on 8 out of 10 Cats Does Countdown, the others are from various different shows and soaps. This suggests that the community is differentiated by its love of soaps, scripted reality shows and entertainment.


What does this all mean?

At its simplist level, if you're an aspiring stand up playing the Fringe then get connected with Dara O'Briain!


There are, however, other uses that the results of the network analysis can help with.


Hosting - Hosts for shows could be chosen by looking at the centrality of a comedian either within a community or the entire network, depending on the specifics of the show.


Collaborations - It could be used to work out which comedians could collaborate with each other. Those that share a link are likely to share a similar audience.


Growing an audience - Comedians could associate with others with whom they don't share an edge (link). The benefit of this would be that both comedians could cross migrate each others followers.


Scheduling events - The Edinburgh fringe could look at a network analysis to decided where to place individual comedians e.g. by having comedians from the same community performing in succession in a similar area. A similar process could be looked at for scheduling TV shows with the aim of retaining and building on viewers.


Material for shows - By looking at the top user accounts that followers of individual edges (links) follow, themes could be identified for new performance material.

Business applications of social network analysis

In this article we have applied network analysis to comedians but it can be applied to marketing and business situations to provide insight.


In the example above the nodes represent comedians but they could just as easily represent a brand, a product, an organisation or a service. In an international network analysis, each node could be a country.


Edges, or the links that connects nodes, represent relationships between them. In the example above they represent Twitter connections but they could also represent buyers of a product, users of a service and strength of feeling in relation to brand attributes.


Twitter is a great source of data for network analysis but it is not the only one. Survey data, a CRM database and even large volumes of unstructured text can be utilised. Network analysis does not have to be quantitative, it can be done qualitatively too.


  • Network analysis can be used to understand how the market operates by graphing the network of brands or products in the competitive set. We can calculate the centrality measures to assess things like a brand’s power, activity and communications effectiveness. This will identify what a brand needs to focus on in order to grow.


  • Network analysis can be used to generate a segmentation. The analysis will identify clusters of people within the same consumer or social circles. Often this can be related to stated needs. From this you can identify the cluster with the most influence or those most likely to spend and target your marketing accordingly.


  • It can be used to identify marketing messages that resonate by undertaking a keyword analysis. In a keyword analysis, first a network map is created to understand how the various keywords are linked (based on their associated connotations) to a brand. Based on this mapping, various messages can be created to suit the needs.


  • Network analysis is really good for getting a detailed understanding of service use, needs and gaps. Our researchers used network analysis to qualitatively map formal and informal support providers for people with a life limiting medical condition. It identified the hierarchy of support services required and where investment was needed to provide new services.


For more information on how we can apply network analysis to help your business grow, please contact us.

by Michael Wagstaff 8 April 2025
The huge volume of data available through consumer comments, reviews and surveys can make cutting through the noise difficult. In this article we discuss how text analytics combined with human expertise can uncover the insight.
by Michael Wagstaff 10 March 2025
Market research agencies are going all in on AI based models to generate next level consumer insight. But are these just more illusion than substance?
by Michael Wagstaff 3 March 2025
With the online survey already on the ropes due to poor quality, has data science finished it off?
by Michael Wagstaff 24 February 2025
Research agencies are pinning their futures on AI. Are they right to do so or are we missing trick by ditching the human?
by Michael Wagstaff 12 February 2025
Online surveys suffer from fake, ill considered and unrepresentative responses. What can be done to improve their reliability? Triangulation is the key.
by Michael Wagstaff 11 February 2025
With so many agency panels riddled with fake respondents resulting in poor quality data, are we witnessing the end of the online survey?
by Michael Wagstaff 6 February 2025
With the January transfer window closed, we run our predictive model to work out the probabilities of where each team will finish in the final Premier League table.
by Michael Wagstaff 5 February 2025
In this latest article in our series on the power of text analytics we look at how sentiment analysis can be used to really understand what customers think about product offerings.
by Michael Wagstaff 23 January 2025
The true value of review sites lies in going beyond the stars and analysing what reviewers are actually saying.
by Michael Wagstaff 17 January 2025
Start making sense of customer review and feedback data by using text analytics. In the first of a series of articles we discuss how it can help your business.
Show More