Gilad Lotan » twitter

Recent Media Coverage

gilad — Mon, 16 Jan 2012 02:01:34 +0000

Over the past couple of weeks I’ve been honored to have my work has covered in a number of awesome publications.

Viral Information Flows / MIT Technology Review

Mike Orcutt of MIT’s Technology Review published a fantastic post, Information’s Social Highways, available in this month’s magazine as well as on their website. Mike got in touch with me over the summer. He wanted to highlight various interesting aspects of information dissemination within social networks, including their visual representations. We threw around a number of ideas and agreed that it’d be fantastic to identify a number of interesting information flows that emerged from Twitter, visualize, and highlight similarities and differences in the way their networks had formed.

A quote from the article:

There is no recipe for virality, says Gilad Lotan, head of R&D for a startup called SocialFlow, which aims to help clients from the Economist to Pepsi more effectively capture attention on Twitter. But the deluges of data that viral tweets generate hold potentially valuable insights into how and why certain things spread beyond their author’s network of regular contacts.

The article compared two very different information flows. The first, providing hot information about the Osama Bin Laden operation, was incredibly fast. Within a few minutes, there were over one thousand users reposting the message, along with prominent journalist accounts. In comparison, the second flow is one initiated by my close friend Deb Chachra. In reaction to the London authorities threatening to shut down Twitter during the riots this summer, she posted the following tweet:

Urban rioting existed before SMS/social media. You know what didn’t? Large-scale community cleanups, spontaneously organized within hours.

Her post went viral, but in a very different manner. Over a period of two and a half days, Deb’s tweet saw a sustained growth in the number of folks reposting it. Every few hours, the post would get a boost from someone with a large audience who reposted it, continuing on this way. While in the previous example, the path to an important curator (Brian Stelter) took one minute and not more than one hop, in Deb’s case, it was several hours and 11 hops before the message reached Graham Linehan (@Gilnner) who has a large audience with which the message resonated.

Mike wraps up the article, making the case for what we do at SocialFlow:

Being heard isn’t always easy in an age when anyone can become a broadcaster. But analyzing and visualizing such data helps SocialFlow guide customers about how, when, and what they should tweet to have the best chance of disseminating their messages widely.

News as a Process: how journalism works in the age of Twitter / GigaOm

Mathew Ingram published a piece called ‘News as a Process: how journalism works in the age of Twitter‘, on GigaOm covering our IJOC study – “The Revolutions Were Tweeted: information flows during the 2011 Tunisian and Egyptian revolutions“. Matthew highlights one of our key findings on homophily within Twitter’s media ecosystem: journalists tend to retweet other journalists, bloggers tend to retweet other bloggers, and so on). Finally, the article links to the visualization I posted on Global Voices, highlighting GV authors who were central figures in disseminating news about the turn of events during the height of the Tunisian and Egyptian revolutions.

Network of news dissemination during the Tunisian and Egyptian revolutions (green nodes are Global Voices authors)

Quote from the article:

As we look at the way news and information flows in this new world of social networks, and what Andy Carvin has called “random acts of journalism” by those who may not even see themselves as journalists, it’s easy to get distracted by how chaotic the process seems, and how difficult it is to separate the signal from the noise. But more information is better — even if it requires new skills on the part of journalists when it comes to filtering that information — and journalism, as Jay Rosen has pointed out, tends to get better when more people do it.

Visualizing.org

Lastly, the Osama Bin Laden Twitter visualization that I worked on earlier in May 2011 was highlighted as one of Visualizing.org’s visualizations of the year. wo00t! For those of you not familiar with Visualizing.org, it is a fantastic community of creative folks with the goal of making data visualization more accessible to the general public. The site hosts hundreds of datasets, and encourages users to create visualizations through challenges which run on the website.

I’m extremely excited and humbled by the range of awesome coverage!

Now – back to work

Reaction to Brian Solis’s Interest Graphs

gilad — Fri, 25 Feb 2011 16:58:16 +0000

I was pointed to the following blog post by Brian Solis, The Interest graph on Twitter is Alive – studying Starbucks top followers. Brian’s post defines an “interest graph” as a subset of the social graph around a certain topic. He claims that while Social Graphs of follower/following relationships were interesting, the interest graph is a step beyond, it is a focused network that shares “more than just a relationship”. While I’m a strong believer in topical graphs (I’ve been creating them for various analyses over the past couple years), I find his argument generalized and terminology around data problematic. There’s a lot of hand waiving, and little acknowledgement of the assumptions and biases of the data that’s coming from public Twitter profiles.

“While we are what we say in our Tweets, our bios also reveal a telling side of who we really are.”

Our tweets represent moments of time in which we displayed interest in a topic, person or thing, while our bios represent our aspirational selves. There are so many more people who write “activist” or “blogger” in their bio, whom in real-life wouldn’t be considered either one of those. Additionally, stated location is usually only updated upon profile creation and never touched again, thus making it obsolete in a highly mobile society. Only about 10% of users share geo-location while Tweeting, which leaves us with a lot of guess-timation work.

Statistical Bias
It is extremely important to keep in mind that Twitter is used by a subset of the population. Of course many users will use the terms ‘geek’, ‘technology’ or ’social media’ in their bios! There’s substantial statistical bias when looking at Twitter across the board, so as a brand, you must not consider a Twitter audience as representative or your real life audience, but rather a slice.

Shminfluencers
Solis throws the term ‘influencers’ around. In one case, he links to this ReSearch.ly page that supposedly points to “Starbucks influencers”. However all I can see on top are spam bots

or foursquare checkins:

Or people who mention the word ’starbucks’ in their tweet. I see no “influencers” in this list, nor do I suspect any of these posts affected others to gain more interest in the brand. By generalizing across anyone who posts the term ’starbucks’, research.ly is contaminating its data. And this is precisely my point of contention with Brian’s post.

Graphs of Influence

Influece is complex. Certainly not binary. Influence is represented by a hodgepodge of human behavior, social dynamics and serendipity. Many experts are trying to define it, and the truth is, there’s no recipe. Solis calls a version of this the ‘brand graph’ – a group of highly connected individuals within a given topic. Apparently the tool looks at users who mention the term ’starbucks’ and then sees if their followers also mentioned the word ’starbucks’. Assuming that this represents a transaction of “influence is naive.

1. How do you account for timing?
2. Do you even look at whose following who? Perhaps a user was influenced by another profile who mentioned “starbucks”?
3. Maybe there was no influence at all. There’s a well-known property within social networks called – homophily (birds of the same feather stick together). We tend to connect with people who are similar to us. Most likely my friends will talk about topics that interest me. Doesn’t mean that i’m influenced by them.
4. Even if we agree that user A mentioned ’starbucks’ because she saw user B posting about starbucks, why do we automatically assume that this is influence?

Before using the term influence, we must understand and acknowledge where our data is coming from, and its statistical bias. We must understand that Twitter is a highly engaging conversational space. And if we’re seeing a conversation about a topic, there doesn’t necessarily have to be a transaction of “influence”. We shouldn’t use that term lightly.

Interest Graph + Social Graph = Magic

While both the social graph and the interest graphs are interesting on their own, the real magic happens when we put them together. By overlaying the dynamic topical discussions on top of the social graph, we are able to identify clusters of users engaged in conversation over a topic. By following the spread of these topics, or the information cascades, we are able to start mapping out the spread of topics across the network. And by analyzing structural positioning of users (within the graph), we can start to get a sense for their level of influence, in creating and sustaining information flows.

#Sidibouzid Twitter Hashtag: an analysis of the people spreading the news

gilad — Mon, 24 Jan 2011 14:53:53 +0000

There have been numerous articles and discussions on the role Twitter played during the recent Tunisia uprising. An excellent Techcrunch post by Alexia Tsotsis analyzed Twitter traffic over time (using data provided by backtype. According to their report, Tunisia related Twitter traffic peaked at 28 tweets per second, at 21:27:56 Tunisian time, a couple hours after the first reports that Tunisian president had left the country. At the end of the cycle, total tweets mentioning Tunisia were over 196K. Total tweets mentioning #sidibouzid (the provice where the protests started) were over 103K.

While this is great analysis on the content itself, I found little to no analysis of the participants on Twitter. Who are these people that chose to pass on and amplify messages? How did the information spread? Who were pivotal points that enabled this? By answering some of these questions can we reach a understanding on the role that Twitter plays in diffusing information to public attention around the world?

Participating Users

My dataset includes 170,000 Tweets all containing the term ‘#sidibouzid’, posted between Jan 12th and 19th by some 40,000 different Twitter users. This is not the complete dataset, but what I could grab using the public Twitter APIs. The following chart below maps out the distribution of Twitter users who joined the conversation by posting a message with the ‘#sidibouzid’ hashtag. We see a huge spike between Jan. 13th and 14th, reaching almost 12,000 new users at its peak. This is not surprising, given all the other analyses pointing to a huge spike in “attention” that the story received on Jan. 14th, when Ben Ali fled Tunisia.

Participation amongst users (i.e. – number of times users posted a message with the ‘#sidibouzid’ hashtag) follows a power-law distribution:

Top 10 participants of the Hashtag (in terms of volume posted) are:

Some of these accounts are broadcasting into the ether, like our top participant, griffinworks_3. This profile was only created on January 12th 2011, has since then posted around 4,000 Tweets, and has acquired only some 100 followers. From my dataset, looks like this profile got around 20 ReTweets between Jan. 15th – 18th. Not much activation, nor audience. The profile also doesn’t follow anyone else. Possibly a bot that auto-forwards content.

On the other hand, if we look at Dima_Khatib, an Arab journalist with Al Jazeera, we see an extremely active profile (over 9,000 posts) who is quite new to twitter (created mid October, 2010), but with a high following of almost 5,000, and a high rate of mentions/RTs (over 5,000 times).

User Bios

Using wordle to visualize the users profile information (the “write something about yourself” field), it is quite clear that as the events unravel and spread out to the world, we see a drastic shift in the kinds of people who are joining the hashtag. Dominating words that represent the initial Twitter participants are ‘Tunisian’, ‘journalist’, ‘politics’, ‘activist’, and a variety of French stop words:

Once the topic started trending, we see the people joining the hashtag represented by the following words: ‘news’, ‘twitter’,'music’,'marketing’,'media’,’student’…

Geographic Distribution

What can we learn about the spread of this topic by looking at people’s geographic location? If we had a precise indication of every profile’s exact location, this would be fascinating. My assumption is that we would see small discussions happening around the Middle East, France and Morocco in the days before the uprising. Relatives and Tunisian expats from neighboring countries sould be Tweeting about the events, much before they reach world headlines. Could we actually see how the conversation moves from being regional/local into global? And if so, what does that movement look like?

There are three profile attributes that can give us clues about someone’s location: 1) User inputed ‘location’ field 2) User inputed ‘time-zone’ field 3) geo-location. When a user creates a Twitter account, the Time Zone may be automatically updated to the current location (depending on browser and connection), otherwise it receives the default value of ‘Quito’. Tunisia and Paris share the same timezone (CET). If someone in Tunisia creates a new profile, their timezone may automatically be set to ‘Paris’. The location field has no default, while the timezone field receives a default value of ‘Quito’. This makes it extremely tricky to draw solid conclusions out of the timezone field.

Since only 15% of users enabled geo-location, I chose the location field as the best indicator. Since it has to be entered manually, it may not be the most updated location, especially if the profile travels, but at least indicates a solid connection between the user and a country. For this analysis I chose to look at all profiles who stated their location.

Its interesting to see how comparatively strong of a role Egypt and France play initially:

And then how Saudi Arabia, Indonesia the US and UK folks get heavily involved:

Social Graph and Connectedness

Knowing how an individual is embedded in the structure of groups within a network may be critical to understanding his/her behavior. For example, some people may act as “bridges” between groups (connectors or “brokers” of information). Others may have all of their relationships within a single group (locals or insiders). Some may be part of a tightly connected and closed elite, while others are completely isolated from this group. Such differences in the ways that individuals are embedded in the structure of groups within in a network can have profound consequences for the ways these “nodes” receive information or reach an opinion.

This is probably the most interesting part of the analysis, but also the most complex. I used the Twitter API to mine the publically available relationships between all hashtag participants. There are two important measures that I used to make sense of all this data:

In Degree: how many users who participated in the hashtag are following this person. Effectively, how popular/reputable this person is within the group of all those participating.

Clustering Coefficient: measures how closely clustered this person’s “neighborhood” is inter-connected. If all your followers and friends are friends with each other, your CC will equal one.

I chose two different participants so that I could map out their network and see what we can identify.

ifikra
The graph below represents Sami Ben Gharbia’s network. Sami showed up as one of the most prominent Twitter users on January 13th. He was one of the most central nodes within the group of people who were passionately posting the ‘#sidibouzid’ hashtag prior to the peak of events. Sami shares a large chunk of his audience with two key users: an Egyptian journalist (mfatta7) and a Channel 4 News foreign affairs correspondent (jrug). This is a mapping of only his first degree followers and friends:

Dima_Khatib
The following graph represents Twitter user Dima_Khatib’s network. Dima_Khatib was one of the most active participants, posting over 800 messages to the hashtag. Dima is a journalist at Al Jazeera, and as I mentioned previously, is quite new to Twitter (began tweeting in October ‘10). Dima shares a number of her audience with a fellow Al Jazeera journalist (Mskayyali):

SBZ_news
SBZ_news is a profile that functions as a typical broadcast media outlet, with a very high in-count, yet a very low out-count (has many followers, and follows almost none). Whats interesting here is that its community of followers includes a number of key players, who themselves have a fairly large audience. This seems to have been an important source of information from the ground in Tunisia.

What Next?

This post is merely touching the tip of the iceberg. There’s still so much that can be understood by slicing and dicing this data. As we start to grasp the power of Twitter as a worldwide information diffusion network, we must build tools that help analyze the structures that enable information to flow.

Understanding Information Flows: the True Power of Social Media

gilad — Wed, 19 Jan 2011 18:56:33 +0000

With all the excitement about Tunisia and the numerous debates on whether this was/is another “Twitter Revolution”, it was the perfect time to dig into Clay Shirky’s recently published piece ‘The Political Power of Social Media’ in the Journal for Foreign Affairs. I actually like the journal and usually buy a copy, but sadly there’s no existing text online, which means, the article is not part of the current debate (a shame!). Many agree that the revolution in Tunisia did not happen because of Twitter, nor did Twitter *actually* help much for those fighting in the streets of Tunis. While social media play an important role in easing the flow of information during and after the peak of events, Clay argues that there’s an important and usually overseen long-term effect that Social Media has in strengthening public spheres.

In the article, Shirky claims that the US government overestimates the value of access to information, particularly that hosted in the west, and underestimates the value of tools for local coordination. There’s a need to think of social media as long term tools that can strengthen civil society, and thus the public sphere. Clay argues that a strong public sphere plays a crucial role in social change. For example, communication tools during the Cold War did not cause governments to collapse, but they helped the people take power from the state when it was weak. They played a supporting role in social change by strengthening the public sphere. It is imperative for the US to rely on countries’ economic incentives to allow widespread media use. It should work for conditions that appeal to states’ self-interest rather than the contentious virtue of freedom, a way to create or strengthen countries’ public spheres.

Clay describes a fascinating study of political opinion by sociologists Elihu Katz and Paul Lazarsfeld:

in a study of political opinion after the 1948 US presidential elections, sociologists Elihu Katz and Paul Lazarsfeld discovered that mass media alone do not change people’s minds; instead there is a two-step process. Opinions are first transmitted by the media, and then they get echoed by friends, family members, and colleagues. It is in this second, social step that political opinions are formed. This is the step in which the Internet in general, and social media in particular, can make a difference. As with the printing press, the Internet spreads not just media consumption but media production as well – it allows people to privately and publicly articulate and debate a welter of conflicting views.

The fascinating thing about Twitter, is that for the first time, we are able to actually SEE some of these psychologically triggered processes happen. We see the described first step happen all the time: media outlets and corporations tend to broadcast messages using their accounts. These messages may or may not be picked up by the general audience who follows their accounts. But the second step is where things get really interesting. Posts may be picked up and echoed by friends, family members and colleagues, sometimes bounced around so much that the messages turn “viral”.

This second step, the social flow of ideas and opinions between people based on realtime public data is at the crux of an emerging new field that fuses machine learning and statistics with the social sciences. Access to information is important, but understanding information flows is truly powerful in order to do in-depth analyses of people’s behavior and create systems that are smarter and substantially more effective. Clay talks about a notion of ’shared awareness’ – people who are part of intertwined networks, posting and consuming each other’s information. Shared awareness binds and strengthens groups, helping millions who are not part of any hierarchical organization spread messages and reach a common understanding. Understanding how people are inter-connected not only helps us build better systems, but also helps us get a sense for the strength of a country’s public sphere.

As the web continues to evolve into a dense network of social links, we need to focus on getting a better understanding of networked information flow. Additionally we must build tools that will help us slice and dice massive social graphs of nodes and edges. Whether a breaking news story, social coupon or a TV show, information flows are the underlying force powering the web, and affecting the DNA of our society. I am certain that making sense of them will bring huge rewards.

Seeing your Invisible Audience

gilad — Thu, 02 Dec 2010 19:42:21 +0000

::Making Sense of the Ebbs and Flow of Social Data

Below are notes + slides of my presentation at the BRANDSconf. I’d like to acknowledge Hunter Whitney. Portions of this content were based on a discussion and an upcoming article he is writing on this topic (link coming shortly):

I’m extremely passionate about data analysis and design. My work focuses on the intersection of the two. I play with data, and figure out ways to make it more accessible to people. I’m here to talk about why the art of making sense of massive amounts of social data is critical not only for geeks like me, but any professional using Twitter. And my goal is to get YOU all excited about the opportunity that understanding data unveils for us.

Whether you’re a multi-national enterprise, a local deli or a mah-jong meetup, the proliferation of social network services like Twitter have created an expectation that you interact with your customers, users and followers. There’s an expectation to connect rather than broadcast. We’ve been hearing this over and over this morning – you are a brand. And as a brand you are expected to interact with your audience like a person would interact with others. You need to engage in conversations, provide and receive feedback, network, create hype, and do all this in a timely manner.

But how can we be expected to interact with an ever growing and diverse group of people when we can’t really “see” them?

Giving Shape to our Audience

Judith Donath of Harvard’s Berkman Center talks about human signaling and how that translates to digital spaces. I get a variety of signals from merely standing in front of you all – your age, what you’re wearing, how you’re feeling, whose smiling and whose already fallen asleep. Being here, with you, part of this event, I have context that helps me understand how best to interact with you all. I’ll happily switch to speaking Hebrew, but obviously that will not be helpful. Even the little bit that I know about you helps me make some useful assumptions – speak English, tune down the analytics/mathematics terms, tune up the user experience/brand jargon.

Social network spaces are fueled by social interactions. Think of people’s interactions online as digital breadcrumbs, trails of connections, likes, thoughts and opinions. By piecing together these crumbs we can start making sense of the people giving us attention on Social Network sites. We must use as much of the tools available to mine the data about our audience – location, time of day, language, interests. In order to interact with an audience we need to be able to sense it.

There are a variety of tools that give us this opportunity to mine content. This is only the first step. We need to put an emphasis on looking at the connections between people, and not only the content that is being published.

The Social Graph

Social Graph is a term that I’m certain you all will hear more and more as social network spaces become a fundamental component of our lives. A social graph is a dataset that represents people and their inter-connections within a group. Mark Zuckerberg is known for popularizing the term in his description of the value that Facebook Connect brings to websites. Facebook’s social graph is made up of you all who I’m sure have accounts, and all your connections. Additionally, that graph distinguishes between types of connections – whether colleagues, friends or family.

Twitter’s social graph is different. Its a directed, which means that connections have directions. The person who you follow does not necessarily follow you back. Twitter’s social graph is fascinating because it maps people’s interests; what people are willing to give their attention to. By understanding people’s interests over time as well as their interconnections, we have the ability to identify we can reveal valuable points such as (1) bridges: people who connect two distinct communities (2) influencers: those who can get their audience to participate (3) experts: people who specialize on a specific topic (4) hustlers: culture creators.

While it is fairly straightforward to aggregate large datasets, we are still challenged by making sense of graph based data. These constantly changing graph indexes are massive at scale and may require complex queries in realtime: whats the shortest path between person A and person B, whats the intersection between group C and D or whats the clustering coefficients amongst group E. Once calculated, these results reflect on the intricacies of people’s relationships, and shedding light on properties that directly affect their behavior: influence, trust, authority and personal preference.

Understanding information flows

In the social web, information spreads through people, networks of friends, fans and followers. Social network sites create compelling spaces where users feel comfortable to hang out, interact, consume, poke and publish. Social interactions lubricate the flow of information within these spaces, creating a plethora of dynamics. These spaces are filled with endless streams of content, encouraging users to participate, add to, consume from and redirect content. As information flows by, users grab content when it is most relevant, valuable, entertaining or insightful, and at times, choose to pass it on.

Because information flows through networks of people, attention has become a scarce commodity. This is truly a game changer. Media companies no longer control people’s attention, but are rather fighting for a smaller section of the pie. True power lies in understanding how information flows and its effect of where people choose to focus their attention. In order for messages to propagate through social networks, people along the way must be attentive to the pieces of information, see them at the right time, and pass them onwards.

Whether you’re interested in socializing or in selling a product, understanding people’s habits around information consumption and production is imperative to attaining people’s attention and building an audience. By leveraging the publicly available data around people’s practices, we can create services that shed a light on people’s habits and preferences. Additionally, by mining this data over time, we can infer their value in affecting information flows.

::demo:: seeing a Twitter Hashtag Spread

I’ve been following @jeffpulver for a while now and know that he’s quite generous in terms of attention. A great time to catch Jeff is in the morning (wherever he is), as he sends out a ‘good morning’ Tweet, there tend to be reciprocal pings and messages. I also know Jeff is interested in new developments in the Israeli startup scene. If I have any juicy piece of information on that topic, I’d make sure to post it, possibly with a /cc/ to Jeff, and ideally around his morning time. I have a mental model in my head, around Jeff’s practices in consuming and producing content.

We all do this, but can only capture so much in our heads. We need tools that scale and capture our networks as a whole and not just individuals. Remember, its not necessarily about the size of an audience or someone’s number of followers, but rather who they are and who they’re connected to.

That all sounds really great, but in effect, representing large graph datasets can easily get out of hand, however loved by geeks, usually becomes a tangled mass of lines and dots. We must remember that this data is beneficial only if people are able to make sense of it. We need to think about interfaces that will let us play with the data; slice and dice the parts that we deem relevant or interesting. In addition to an intuitive interface, we need controls that will help us dive into and observe patterns or connections that would have otherwise been hidden.

Closing

There are three points I want to make sure you all come out of this talk thinking about:

1) Mine Digital Breadcrumbs – use the exiting tools to get a sense for how our audience looks and its segmentation (I’ve made a oneforty kit here)

2) Social Graphs are Extremely Useful – yet complex to aggregate and mine.

3) understanding information flows is Powerful – especially as we’re shifting from broadcast mode to that of engagement

Social network analytics tools may fundamentally change the way we engage with our online audiences. We need to build better tools that do the above mentioned tasks. But I need people like you all to be vocal about your needs and frustrations. As we’re building out these technologies, we want to make sure they are tailored to real needs. We’re only at the start of the journey, and I’m super excited to be a part of it!

Aerogel Installation at TEDActive

gilad — Sat, 20 Feb 2010 04:37:47 +0000

I was fortunate to be invited this year as one of the contributing artists at TEDActive. This is the simulcast event that happens in Palm Springs at the same time that the main TED event takes place in Long Beach. The organizers frame it not as “TED jr.” but rather a more intimate version of TED; in essence, what it used to be like before it became a 1500 person event.

Ironically enough, Bing sponsored a really cool lounge which included a number of interactive art pieces. This is were Dan Goods and I installed a variation the Aerogel installation. For TEDActive, we slightly altered its interactivity and the projected material:

Aerogel is a solid made up of 99.8% air and 0.2% of a smoky form of silicon, hence its other name: ’solid smoke’. While it is easily breakable, the material is super light and a fantastic heat insulator. Throughout the week, Dan would let people hold a piece of Aerogel on their hand while directing a blow-torch at it. When projected upon, it captures light in a stunning way:

NASA uses aerogel to capture dust particles in space. These particles vaporize on impact with solids and pass through gases, however can be trapped within the aerogel. Our installation dealt with this notion of capturing that which difficult to hold or grasp. As the conference progressed, the ideas that were raised and discussed during the talks were captured and projected on the aerogel pieces. At different times, a variety of topic would be projected within the aerogel pieces. When left by itself, the projections morphed between movement and colors. But as a person would move their hands in front of the installation, some of the most recent messages posted on Twitter about TED or TEDActive would explode within the projected space.

Here’s a video demonstrating the material’s amazing capability to capture light:

Here’s another video showing Dan interacting with the piece:

Seeing a Twitter #Hashtag Spread

gilad — Wed, 20 Jan 2010 20:51:05 +0000

#CheeringForTheYankeesIsLike is a hashtag created by @mattsly the morning of October 26th. He submitted the following snarky message – ‘Go Phillies. #CheeringForTheYankeesIsLike hoping investment bankers get really huge bonuses of at least 8 figures‘ – hoping to entertain his friends, and possibly get others to participate. Matt had 182 followers at the time, not sizeable by any means on Twitter. Little did he expect that some 9 hours later, 271 different users, most of whom have no connection to him whatsoever, would participate, posting around 500 messages in total.

How did this happen and what prompted this message to spread?

#CheeringForTheYankeesIsLike

About an hour after Matt sent out his first message, one of his followers, @lizzieohreally, wrote the following message ‘@jaketapper? @abcdude? …Hoping someone w/ more Twitter than I can help popularize #CheeringForTheYankeesIsLike (via @mattsly)‘. Lizzie clearly understood that in order to get many others to play, she would have to get someone with a large set of followers to participate. Lizzie had only around 500 followers at the time, so posted this message in an attempt to seek @jaketapper or @abcdude’s attention.

Sure thing, some twenty minutes later, @abcdude see’s the message and adds his own variation to the meme: ‘#cheeringfortheyankeesislike pulling for Regina George in “Mean Girls.”‘ He enjoys it so much that he promptly posts another message and attaches the hashtag. @abcdude is a new york based correspondent for ABC news. He dubs himself a RedSox fan and a cosmic power broker. Not as cosmic as Lizzie had hoped, but still, he has some 7,000 followers, which could certainly help give the meme some traction. We see a small spike after @abcdude’s participation, and by now, some 3 hours after Matt sent the original message, there have been 34 different messages posted with this unique hashtag.

But it wasn’t until @jaketapper joined in that the conversation really took off. The hashtag came to Jake’s attention after @DetourJazz, whom he follows, participated. Jake reacted by posting: ’RT @DetourJazz: #cheeringfortheyankeesislike rooting for “Craterface” in Grease to beat Danny (via @Laura_Martin)’. He then added a new message that he posted to his followers. Jake is a senior White House correspondent for ABC news with over 30,000 followers. Before he took part in this meme, new posts appeared at a frequency of one every 5 minutes. Immediately after he joined, we see a sharp rise in participation, with multiple messages from a variety of users every minute.

Seeing it Spread

1. Graphing the Network – Every user who participated in the meme is represented by a gray circle (Matt, whom first started the meme, is shown in yellow). Edges represents the person who most likely influenced the other to first participate.

2. Seeing the Flow – in this applet, a user is represented by their twitter icon. As the timeline moves forward, each profile lights up when they post a new message with the hashtag. Tthe moment that @jaketapper chose to participate is evident – there’s a clear, sudden spike in participation after his profile picture lights up.

3. Seeing the distance – the following applet highlights the total social distance that this hashtag traveled between users. Each user is represented by a circle, the more influence a user has, the larger their circle is drawn. Edges in this example represent the social ties – when there’s a follower/friend relationship between two users, a line is placed between their representation on the screen. The first column includes only Matt who first used the hashtag. The second row consists of only those people he directly influenced to participate (his followers). While there are a total of 9 columns, it is crystal clear that the most important phase happened in the second and third column, when a core cluster of users chose to participate, and a mini tipping point was reached.

Parsing the Data

#CheeringForTheYankeesIsLike lasted for a total of 9 hours that day, activated 271 different users and included around 500 messages in total. From looking at this meme, it is clear that on Twitter, there’s great advantage to having many followers if one intends to spread a message. It is also clear that having the right followers is key. If it were not for @lizzieohreally who knew to actively pass the message onwards to heavy Twitter users, the meme would never have spread out the way it did. In order to come to these conclusions it was necessary for me to look at social ties in addition to the semantics of the messages posted.

I used the Twitter API to discover the follower/friend relationships between all users who participated in this meme. This is extremely important data, especially when modeling the flow of participation and influence within this hashtag. For example, lets look at a simple case where user B follows user A. If user A first participates and is followed by user B participating, user A is rewarded some number of influence points – this is assuming user B saw the hashtag posted by user A, and decided to participate. Additionally, if a user is retweeted or ‘@’ messaged they are rewarded some number of influence points. Real life situations can easily become complicated, as user B might also be following user C, who participated in the meme as well. Now how do we know if user B was influenced by user A or user C? Hard to tell, but we can build an influence model that takes these situations into account, which is exactly what I did.

Translating the semantics and social ties from the dataset into a visual language that made sense was key to helping me understand this hashtag experiment. I am a big fan of visualization as a means to parse large datasets, however dealing with social, implicit data is tricky, and extremely challenging to represent visually. But when done right, these representations can shine a whole new light and hopefully help us better understand some of the dynamics at play.