Category Archives: Blog

Pulsar update: Visibility 2.0

Today we are introducing a new updated version of the Visibility algorithm that’s powering the Pulsar platform: Visibility 2.0.

The main reason why Pulsar is called Pulsar is that the whole platform is built around the idea of making it easier for anyone to sift through vast amounts of social data by making “important” social media content more “visible”.

One of the key ways Pulsar does this is through its proprietary Visibility algorithm. The algorithm defines “importance” as the ability of a piece of content to reach a larger then average audience and engage a larger than average crowd. The algorithm weights every content on the platform and applies a Visibility score to each post which is then available amongst the metadata used to index and filter the data.

Since we launched Pulsar the Visibility Algorithm has been one of the pillars of the platform allowing you to slice any data view (e.g. trends, influencers, topics) by Volume of data or by the Visibility of the content analysed. Below a series of comparative screens that show how different the same social data looks like when analysed by Volumes vs Visibility:

Posts per Day VS Visibility per Day


Sentiment Volume per Day VS Sentiment Visibility per Day

Top Posts by Volume vs Top Posts by Visibility
But the web is an ever-changing ecosystem: new channels are born, new behaviours are introduced, old behaviours evolve to a new scale or disappear and new ways of measuring them are introduced on a weekly basis. In an effort to keep up with the evolution of the web and continue to deliver effective measures of reach and engagement, over the last three months we have been working hard updating the Visibility algorithm.

The new algorithm takes into account:

  • New sources of engagement data, which are now factored in the calculation of reach;
  • New sources of online viewership data which are now factored in the calculation of reach;
  • New sharing and engagement metrics introduced by the new channels we have integrated, such as Tumblr;
  • Raising levels of engagement across all channels resulting in a need for new engagement and reach benchmarks;
  • New behaviours introduced by new channels like Tumblr, where for example the “weight” of a reaction (a re-blog) is completely different from the weight of a reaction on Twitter or Facebook.

Overall, the new algorithm introduces three key improvements:

  1. More accurate audience size estimates for all channels, particularly for News, Blogs, Forums and Review sites;
  2. More accurate engagement figures across all channels;
  3. A more balanced cross-channel view of reach, to enable effective comparisons between the reach of top down and bottom up media (eg. news vs. tweets).

The new visibility weighting applies from April 10 onwards. However, should you want to re-analyse historical data you can extend the reach of the algorithm to historical data from the Data Management interface in the Results View.

We think the new Visibility algorithm is going to help you run better analysis and make more effective decisions and we look forward to hearing your feedback as you start seeing the new data coming through on the Pulsar platform.

If you are not yet using Pulsar and want to know more about Visibility and Pulsar get in touch here.

Identifying Influencers with Social Network Analysis

Part 1 of our Network Analysis for Market Research series by Rob Parkin – read the introduction here.


In our work as social media researchers we are regularly answering clients’ questions about online influence and influencers. They know that they’re not the only force influencing perceptions of their brands, and they want to reach out to the other people who are. This could mean identifying the right bloggers to bring on board to increase the likelihood of a successful social campaign, or tracking who is most shaping a discussion about a brand or topic.

Pinning down who is influential isn’t straightforward. The data hardly ever exists to connect a social media message with the actions it may have inspired, such as products purchased or businesses boycotted. Instead what we can really assess is ‘potential to influence’: who’s reaching a big audience, who’s engaging that audience the most and getting a lot of interaction, and who’s demonstrating consistent expertise on a topic. So influence is complex, an outcome of a combination of properties about people, contexts and relationships.

That’s why here at FACE we developed our own proprietary metric to analyse which messages were reaching the biggest audience. Our visibility algorithm assigns each piece of content a visibility score, taking into account the properties of the channel it’s on (e.g. blog content lasts longer than Twitter), the size of the author or website’s audience, and the virality of the post – how many times it’s been shared.

Influencers ranked by Engagement & RTs generated (Pulsar visualisation)

Alongside visibility, we also use Social Network Analysis to understand influence through analyzing the dynamics of online behaviours and relationships. It provides the theory, the algorithms and the software to capture, visualize and explore the data gathered using Pulsar. This can enable us to take influencer analysis to the next level – and it’s what we’re going to discuss in today’s blog.

The role of influencers 

Previous research carried out here at FACE by Francesco D’Orazio and Jess Owens highlighted the role of influencers in how information spreads through social media. It discovered that while influencers may only represent a small percentage of an overall conversation, their role does ultimately shape how information spreads. Tapping into close communities makes content shareable, but top-down influence is essential for content to achieve truly viral speed and scale.

We’ll cover communities in more detail in our next blog, but for the moment let’s understand that influencers play a vital role in shaping conversations, and insight into how their influence is structured can also prove important.

Pulsar_Twitter_Hadfield_Visibility crop for website

Network visualisation of how the Commander Hadfield video was shared on Twitter, with nodes sized by Visibility

Identifying influencers

In essence Network Analysis views relationships as connections. Some people in the network might have only one or two connections (e.g. they only have 1 or 2 Twitter followers), and others might have hundreds or thousands.

So hubs or influencers in networks can be identified by looking for people who are highly connected in comparison to the remainder of the network. Because they’re better connected, these are the people who you may wish to bring on board with an online campaign, to help maximize its chance of successfully reaching the greatest number of people.

So let’s look at an example that demonstrates how networks can help us investigate relationships between nodes and identify influencers.

Investigating my ego network

I’m going to use a very self-centered approach and investigate my Facebook network! I used an application called netvizz to capture the data, and Gephi to perform the analysis.

When compiling a list of influencers you may start with a very basic measure, the number of friends/followers. Using Network Analysis and my social graph, we’ll explore the limitations of this metric, and how we might do a better job.

Introducing my friends & family…..

Rob Identifying influencers 1

In this visualisation the nodes are people who are my friends on Facebook, and the edges are the friend relationships between them. It’s important to note that I’m not on the chart – so the connections aren’t their relationships with me. Instead, the connections shown are the friendships that they have with each other e.g. I’m friends with Amy and Bob, and if Amy and Bob are also friends, there’d be a connection between them. If they’re not friends, no connection.

We can rank nodes by a number of measures; in this instance I’ve chosen degree centrality, which is the number of connections each person has. I’ve used this to determine the size of each node: the larger the node the greater the number of connections. This makes the highly-connected people easier to spot.

We’ve also used what’s called a “force directed layout algorithm” to visualize the graph. This means that linked nodes attract each other and non-linked nodes are pushed apart. So the most-connected people tend to end up towards the middle of the chart.

The first analysis that can be taken from the graph is that a lot of nodes share connections. This why why there is one large giant component in the centre of the graph with lots of highly-connected people all clustered together. This is to be expected as the sample of individuals is taken from my Facebook account, the majority of whom do share common acquaintances.

The thing is, we can also see that the biggest nodes are basically the same size, meaning that they’ve got the same number of connections. This isn’t really telling us the story we need – but using network analysis we can go further.

Identifying Influencers 2

Here we’ve taken the same graph and ranked nodes by betweeness centrality. A betweeness centrality algorithm starts by finding all the shortest paths between any two individuals in the network. It then counts the number of these shortest paths that go through each node. Nodes with high betweeness centrality can be considered information brokers that can connect disparate parts of the network.

The result is a smaller list of potential influencers, pin-pointing the people who are vital in connecting the different sub-networks (i.e. the different social groups) in the wider graph. We have identified four people who are now shown to hold a position of influence on the graph. And the layout of the graph begins to tell us how their spheres of influence are structured.

The person over on the right for example is crucial in connecting two small clusters of individuals to the rest of the graph. I know network analysis has correctly identified this node as an influencer – because she happens to be my girlfriend! So she’s the key person connecting both our families to the larger network of my friends.

How can this work for you?

Admittedly there’s a very short list of people who are interested in the finer details of the network structure of my Facebook graph! Nonetheless it’s an interesting example to demonstrate some of the principles of Social Network Analysis.

What can we take from this example? Using network analysis it is possible to study social groups in-depth, not just as homogenous wholes but understanding them as comprised of dynamic relationships between different individuals. And using data visualization and data exploration it is possible to infer a level of understanding which would be otherwise difficult to get hold of without real-world personal knowledge of the individuals involved.

Using Pulsar TRAC it’s possible to scale this analysis up significantly, sampling mentions by keyword, content or user, and applying network analysis we can powerfully:

  • Identify individual messages driving engagement
  • Explore who is influential in shaping a discussion
  • Map a network of individuals following a brand online
  • Better inform future outreach strategy

Exactly the same methods would apply if we were studying, for example, the community of people talking online about beauty & make-up, or audiophile hi-fi equipment, or photography. We could first find the best-connected people, who a brand might want to target to promote their product to the largest number of people. But we could also find the connectors, the people that allow discussions to travel into new communities and ultimately travel further.

In the next blog in our series we’re going to dive into this further, explore how we can identify communities in network structures and get stuck into some more network analysis previously carried out here at FACE.

LinkedIn’s privacy policy change is really about context, not data

Privacy is currently a hot topic in the market research industry. Some of our colleagues are worried that consumers will stop sharing their data, as Greg Heist discussed in Greenbook earlier this month.

Often, the focus tends to be on researchers’ ability to access data – either data is entirely public, or it is entirely private. But I think privacy is much more than whether or not data is public. It is also about the context of that data. Who is accessing the data and why can be just as important as what data they are accessing. So that’s what I want to discuss with you today.


Image by Flickr user James Cridland

Do ‘oversharing’ teenagers care about privacy?

Teen social media use provides a fantastic illustration of the importance of context as part of privacy. Teens put a lot of their data online. According to a PewResearch survey in 2013:

  • 92% post their real name to the profile they use the most
  • 91% post a photo of themselves on social media
  • 71% post a city or town where they live
  • 53% post an e-mail address.

Being public doesn’t seem to bother them that much. Indeed, 64% of teens on Twitter have public profiles, and a good percentage, 12%, don’t even know if their tweets are public or private.

danah boyd its complicated

But, as any parent of a teen will tell you, privacy is very important to them. But for teens privacy isn’t a simple binary of putting personal information online or not – instead it’s about managing the context of who sees what and engages with what on their profiles. danah boyd, a Principle Researcher at Microsoft Research and Assistant Professor at NYU, has worked extensively with teens around privacy.

As she points out, “While adults are often anxious about shared data that might be used by government agencies, advertisers, or evil older men, teens are much more attentive to those who hold immediate power over them – parents, teachers, college admissions officers, army recruiters, etc.”

Teens try to manage the context of their discussions. For example, according to the Pew survey 58% of teen social media users use inside jokes or other ways to hide the meaning of their messages. They hide the meaning and the context of the messages, not the access to the messages themselves.

I don’t think this emphasis on context is isolated to children. The internet allows us to network, share our thoughts and see the thoughts of others. In many ways, the very public nature of it is the draw. Yet people are still concerned about privacy. To see this dichotomy in action, let’s take the new LinkedIn member blocking feature.

The need to be public, the need to retain privacy

The story of this new blocking feature actually began in April of last year when a petition was posted on asking LinkedIn to implement better privacy features.

linkedin petition on stalkers and privacy

A woman named Anne R. was being stalked by a man who had sexually assaulted her at work. After she left the job, he continued to harass her online. The problem was that, unlike just about every other social media website out there, LinkedIn did not have a block feature. She wanted a professional experience on LinkedIn, but her stalker had other ideas. She couldn’t control her situation, and that was the problem.

Her options at the time were to either change her name on the site or remove herself from the site entirely. But that, she argued in her petition, was in essence sacrificing her networking opportunities in the face of something she was powerless to prevent. In other words, she wanted her information to be public. Just not available to the man who was stalking her.

Anne’s problem wasn’t that her data was public. Yes, that was part of the situation, but what she was concerned about was the social context she found herself in. She wanted to carry on her life, specifically engaging in professional networking on a service that promised just that. What she got was a nightmare. She wanted her data available to other people who would respect the professional context, not to people who would victimize her.

And she wasn’t alone. Taking a quick look at the stories people shared on the petition website, we can see a variety of situations and people. These stories came from both men and women and covered a variety of topics, from digital stalking by an abusive former boss to fears of a harasser finding their phone numbers or where they work.

Taking care with context

Protecting our data from exploitation by companies or spying by our governments is important. I’m certainly not trying to belittle the importance of data management. But I think that treating it as just data removes the human element that is really at the root of these concerns.

People want to control what situations they find themselves in. They don’t want things taken out of context and used that way, or even just have an organization jump in when they were having a nice chat with a friend – regardless that it is on a public site.

As market researchers, particularly social media researchers, we have to understand what the privacy debate is really about. Many are worried that people will choose to stop communicating on open channels where we can access their data. While some behavior may change, I don’t think people will stop sharing on public sites entirely. People like talking and sharing with people they may not know, as well as just with their friends. But they don’t want these public engagements to be taken out of context, or for that context to suddenly change out from underneath them.

As social media marketers, we have to widen the privacy debate beyond the black and white of data access. We have to respect the context of the data, perhaps even try to protect it by helping our clients understand what types of discussions are okay to join and what aren’t, or what types of insights are good to use in ad copy or communications overtly, and which are probably best left as subtext. We need to help our clients respect consumers’ control over context online, not just the access to data.

India’s love affair with WhatsApp

Whats app logo

Earlier this month, a news story broke: “India police use WhatsApp to trace missing boy”.

It’s an  interesting and highly contemporary story. Police in Bareilly took a photo of the pamphlet they had posted all over the city which carried a picture of the missing boy and his father’s contact details, and sent it by WhatsApp to nearby police stations and the boy’s family and relatives. They in turn forwarded the message to everyone in their WhatsApp address books. A man called Daanish  received the WhatsApp message from a friend known to the boy’s father, and recognised the boy in the photo as being on his train. And the rest, as they say, is news!

This story caught my imagination, as another WhatsApp user from India myself. So I thought I’d write a little bit about how I’m seeing the app work in my own social circle – and how I think WhatsApp fits so well into Indian society and culture.

Now, WhatsApp’s not reached the whole of India yet – in fact, the app only rolled out in Hindi between January and March this year. Previously Indian people had to use the English interface, which of course restricts uptake to a more urban and educated social sphere (only about 20% of people in India speak some English, and 5% are fluent.)

But this move into Hindi should see the app gain a wider user-base, making it increasingly important in both the research and the marketing mix. So far the app already has over 40 million active users, the company’s VP Business Development, Neeraj Arora, told Times of India in an interview last month.

What’s up with WhatsApp? 

I don’t currently live in India, but I too am on WhatsApp. The biggest group I’m part of is a bunch of women who were at school with me. When I recently sent out an email to the group, the response I got was, “Please don’t send email – send it through WhatsApp.” It appears that for them this new mobile app has for the most part replaced email, SMS and even social media options like Facebook. The volume of messages I get from this one group is amazing – every day 100 or more. One might be justified in asking whether being on WhatsApp is a full-time occupation. I know I find it hard to keep up.

The messages are quite varied: a chorus of “Good Mornings” every day either through images or text accompanied by a lot of emoticons, greetings for festivals (no matter how minor), images and videos of members of the group as well as their children – and grandchildren, lots of jokes (many of them surprisingly risqué), items of news about the impending elections and sometimes political cartoons (there’s a lot of that going around just now), philosophical or spiritual pieces that have moved or inspired them, as well as more practical things like planning a get together or a holiday, or asking for travel or shopping tips and advice.

It almost seems like their lives are being played out on WhatsApp. Does this sound familiar – like something that was said about Facebook users?

So why’s WhatsApp been such a hit in India?

1. Sociable and social Indian culture

Kinship and belonging are central to the Indian psyche. Indians love keeping in touch with family and friends, and want to know what’s happening with them.  While that can be said about people in other countries and cultures too, among Indians, the sheer size of the family group and the extent of obligation to keep in touch takes it to another level.

WhatsApp is a mobile app, and since the mobile is at hand at all times, the interactions can be almost like conversations and you never have to miss out on anything that’s going on.

Another feature that supports this need for relationships is that WhatsApp allows a fairly large group size (30 people). This means it’s perfect for family groups, friend groups, or company groups to share news, pictures, greetings, instructions, or for people to seek advice from a larger community. With a single message on WhatsApp, the word can go out to up to 30 people.

2. I’m the first to know, and you’d better know it! 

Who’s getting married? What job the prospective bridegroom has, when the baby is due, which colleague just got promoted… you get the gist. Indians love to be the first to know, and to be seen as people who get the news and gossip first.

Each group has a few members who dispense most of the news and gossip, and the rest react with appreciative comments, and quite possibly forward the tidbit on to their other groups!

3. Can’t do without SMS/text

With the advent of mobile and the possibility of SMS, Indians found a way to keep in touch at relatively low cost. A 2013 GSMA Intelligence report shows that non-voice revenues are growing at 16%, twice the rate of voice traffic growth.  And text messaging is 45% of what people are using mobile for. So, when WhatsApp came along offering ‘free SMS’, it tapped right into the Indians’ preferred mode of using mobile.

Whatsapp India 1

4. Love a good deal, and ‘free’ is even better

Using WhatsApp, people can at one stroke both eliminate their SMS bill and at the same time get additional features. The free 1st year (which means they’re hooked!), and low cost thereafter ($0.99) makes it ridiculously cheap, even by Indian standards.

This has encouraged its use, not only by ordinary people, but also by political parties. There’s a general election this year, and political cartoons and jokes against both candidates are all over the social media sites – including WhatsApp. And if the material is funny or interesting, people help in the ‘marketing’ task by sending it on to their groups. For example, I received a WhatsApp message this morning that read “India needs to be MODIfied” (Narendra MODI is the opposition party’s Prime Ministerial candidate).

5. Makes me feel SO good!

Indians seem to need validation and acknowledgement just as much as (if not more than) other cultures. Within a WhatsApp group there’s a great return on a very small investment. The app is very intuitive and easy to use and a wealth of emoticons enables an instant response that doesn’t require much thought. It allows people to maintain relationships and be part of the group with very little effort. As with Facebook, this small effort on WhatsApp brings its users rich emotional rewards – appreciation from many for passing on a joke, poem, piece of wisdom, news, and the sense of solidarity with kindred spirits.

What does WhatsApp’s success tell us?

The image below – which was sent to me on WhatsApp (of course!) – shows what WhatsApp means to Indian consumers

WHats app India 3Translated, it reads:

A way to share the secrets of the heart

A way to remind others of you

A companion who helps you forget your sorrows

And a way to keep your relationships even when you don’t meet!

Firstly, WhatsApp’s success tells us that relationships are important to people, and that’s a domain that marketers and product designers need to think carefully about. How can your product help people have better relationships with those around them?

It also reminds us that there’s definitely a place for products that are simple and focused, and put users’ needs first. The dedicated WhatsApp messenger has succeeded where Facebook’s messaging functionality hasn’t. So there’s a lesson in simplicity here too.

So, now WhatsApp’s included Hindi in its supported languages, we look forward to seeing how the love affair with WhatsApp will spread beyond the English-speaking population to a still wider Indian audience.

An Introduction to our Network Analysis for Market Research blog series

As social media researchers we help clients make sense of people’s online behavior, which is of course complex. While they have their uses, KPIs such as volume and sentiment can only get you so far. One key limitation is that they only measure what people say – not what they do as well.

Social media research is moving beyond keyword tracking, something we’ve been innovating here at FACE with Pulsar’s content and audience tracking technologies. To really dig into online activity, we need to analyse metadata, the information spun off by social behavior, just as much as the messages people produce. And we need to embrace a wider range of methodologies drawn from the field of computational social statistics.

We can do this through social network analysis (SNA), a research framework giving us the tools and concepts to investigate questions such as how content is shared and how communities are formed.

We are going to dive into examples in more detail for our ‘Network Analysis for Market Research’ blog series, covering topics including:

  • Visualising networks to make sense of large & complex data sets
  • Methods for identifying influencers
  • Identifying communities
  • Tracking how networks evolve over time
  • Mapping how information spreads
  • Overlaying networks with other metrics

For great examples of how we can benefit from investigating social structures using network analysis you need look no further that FACE’s research carried out by Francesco D’Orazio and Jess Owens for Twitter on How Videos Go Viral, & How Stuff Spreads: Gangnam Style vs. Harlem Shake in partnership with Datasift.


In our blog series we’re going to investigate methodologies used in these projects, provide additional examples of network analysis, dive into some theory & explain practically what this means for the process of social media research.

If you have any questions about what I’ve discussed in this blog or about our forthcoming blog series then please do get in touch.

Part 1 of the blog series has now been published. Read about Identifying Influencers with Social Network Analysis here