We know social media are going to play an important role in political elections this year, here in the US and internationally, as we saw last month in France with the election of Francois Hollande over the incumbent, Nicolas Sarkozy. Yet upon close examination, which I've been doing plenty of, I've concluded that the methodology and approach aren't yet convincing enough.
In an earlier AllAnalytics.com post, I noted that candidates can buy Twitter followers and Facebook Likes using advertising and suggested the ability to verify a candidate's grassroots support becomes a big-data problem when millions of followers are involved. For purposes of this post, I decided to look at that challenge using the Media Analysis Program (MAP) from Sysomos, a Marketwire company. The figure below, for example, shows how President Barack Obama's popularity across social media has compared to that for candidate Mitt Romney for the period between June 2, 2011, and June 1, 2012.
Keep in mind that two factors skew Obama’s audience (and his social media buzz). One, as the incumbent, his following, especially on Twitter, comprises political followers and constituents along with political watchers all over the world. Secondly, his following is so large -- more than 16 million as of June 1 -- Twitter will not report fully on it due to API usage limits. The ability to measure Romney’s following, which isn't as large as Obama’s, isn't constrained by that limit.
From the figure below, which shows social media activity over the last six months, we can see right away that Romney’s buzz mostly comes from Twitter. Obama has a much stronger presence on blogs and forums, where content typically contains more substance than on the sound-bite-driven Twitter.
Overall, those who are talking about Romney in the blogosphere over the last six months are older and more predominately male than those writing about Obama, as the demographics below show. Doing sentiment analysis on blogs isn’t too reliable, but as far as it goes, Obama has a slightly less favorable sentiment than Romney. We’d need to dig down further, manually, and personally observe how accurate or relevant this information might be (something we don’t have time or space for here). I suppose the political pundits would look at the spread more than the actual percentages/numbers, and go for the center -- trying to get the neutral sentiment to skew positive or negative.
On Twitter, however, Romney’s campaign seems to be shouting louder, having generated 2.3 million mentions, 12,558 tweets per day, and 523 tweets per hour -- compared to Obama's 1.5 million mentions, 8,160 tweets per day, and 340 tweets per hour over the last six months. The Twitter audience is slightly more male for Romney than it is for Obama, at 67 percent compared to 61 percent. The word clouds from Twitter, which is clearly shaping up as the main social battleground for these candidates, show Obama as more concerned with the issues and social media channels, while Romney’s messaging is more about party, race, and other Republican contenders (when there were others). Take a look below, which I compiled using words from the last six months.
With all this analysis, perhaps the most telling information I was able to get ahold of may have to do with the electorate income level. Obama’s followers have much less money and disposable income than Romney’s followers do. This comes from information I’ve pulled out of another platform, PeekAnalytics, but can’t yet detail. Perhaps the 2012 presidential election, more than anything else, will be about those who have the means to live as they choose and those who don’t.
I’ll be attending Netroots Nation this week in Providence, R.I., and hope to come up with some new information on what is meaningful to track for political elections. In any case, I’ll write more on the analytics of politics, local and national, as we move into the summer and fall, leading up to the elections in November.
How closely are you following the candidates on social media? Share below.
Interesting piece Marshall, I really like how you showed what these different social media forms reveal about the candidates for a given time period. I am not personally following either candidate. But it is interesting to ponder the effect these forms have (if any) on those that do follow.
My knee-jerk response to Romney's heavier Twitter buzz is related to a long GOP primary season with a heavy load of negative bloviating from all the candidates. In the digital social world, slander and negativity builds traffic. Obama's campaign hasn't engaged as heavily about the GOP candidate until recently and I am curious to see what the analytics reveal later, say around September at the end of our summer of discontent with all things political.
Taking a cursory look at the Twitter Word Clouds reinforces the observation with Romney's WC showing "Newt", "Santorum", "GOP", "Gingrich", "Iowa", "Paul" and other buzz words from the long cycle of GOP debates. Obama's WC shows fewer GOP characters with less stature (smaller relevant size for Romney or Gingrich) but interestingly with references to Michelle. Ironically, Obama's WC contains "America" and "United" whereas those words are no where to be found in Romney's WC, just a handful of the key states of Iowa, Florida, and Michigan. Take that for whatever it means.
I think social media can provide a lot of insights to where they need to focus on. I'm stealing my friend's and former professor's post on Facebook here (Anne Wenzel).
"Blacks and Hispanics are far more likely to believe that poverty is a result of circumstances beyond a person's control than a result of lack of effort. ... 78% of both blacks and Hispanics believed that government should guarantee everyone enough to eat and a place to sleep, while only 52% of whites agreed with that idea. ... There was very little difference in the percentage of blacks, Hispanics and whites who believed that poor people have become too dependent on government assistance programs (it's pretty high for all three groups, at 70, 69 and 72%, respectively)."
In large part this election will be about the role of government in our lives, and different racial and ethnic groups view that particular issue very differently...A staggering 90% of Romney supporters are white. Only 4% are Hispanic, less than 1% are black and another 4% are another race.
Beth, - Well, you do have a point the value is not provable. However sometimes it does help in determining the likelihood that these people will actually turn out to vote. A candidate could be garnering support from a demographic of people that generally doesn't vote. Lip service becomes all they get then...and this is especially true like in Kenya. The majority of voters are not on twitter. Twitter holds a lot of people from diaspora who in the past didn't have any vote(and even for the upcoming elections we are yet to see how that works). The traditional field rally was and mostly still is the way to go for serious candidates.
Predictability and buzz are two different things. Frankly I think that the campaigns should only be using Social Media for the youth vote. I think in that demographic it is pretty accurate. I think age has more to do with Social Media Buzz than anything. Not so much economics etc. Measuring economics is very complex.
I agree with you that the next four years will be exicting for us but even today we have sophisticated methods to accurately measure the social impact. Text mining, sentimental analysis and social media analytics coupled with mobile and tablet technologies are the hot topics in any analytics forum today.
There is a lot of research going on to answer the magic questions like - What is the value of a Tweet or Like? and I think there has been a fair progress in that domain
But, kickeko, is understanding the age and disposal income of a candidate's Twitter followers all that telling if we're trying to predict election results -- given only a particular segment of the voting public will tweet their opinions about the candidates? I agree it's interesting, but I'm not convinced there's a whole lot of provable value.
Anish -- you kind of hit on something here that I was thinking while reading Marshall's blog -- and that is, "just wait till 2016!" I can imagine that over the next 4 years we'll make pretty big strides in our understanding of how to use and measure social media data. Right now, I think we're in a funky time where everybody is talking about social media measurement but nobody the value of the data collected and analyzed is difficult to prove.
It is interesting to be able to tell even the disposable income of a presidential candidate's followers and their average age. It does give an indication also of how likely the message is to spiral beyond any social media measured since not all people are on it.
I follow my presidential candidates closely on twitter(It is supposed to be an election year in Kenya but that was postponed to next year -- long story). Anyway the candidates have been making a lot of effort to utilize twitter and facebook, although in our case this audience is mainly youth and does not fully represent the whole voter picture.
I love the analysis Marshall. Apart from the media, Sentimental and demographic parameters illustrated, is there a scope to develop an overall global model for prediction? This might include variables like past sentiment, campaign statistics and other national and regional numbers.
LEADERS FROM THE BUSINESS AND IT COMMUNITIES DUEL OVER CRITICAL TECHNOLOGY ISSUES
The Current Discussion
Visual Analytics: Who Carries the Onus? The Issue: Data visualization is an up-and-coming technology for businesses that want to deliver analytical results in a visual way, enabling analysts the ability to spot patterns more easily and business users to absorb the insight at a glance and better understand what questions to ask of the data. But does it make more sense to train everybody to handle the visualization mandate or bring on visualization expertise? Our experts are divided on the question. The Speakers: Hyoun Park, Principal Analyst, Nucleus Research; Jonathan Schwabish, US Economist & Data Visualizer
To save this item to your list of favorite AllAnalytics content so you can find it later in your Profile page, click the "Save It" button next to the item.
If you found this interesting or useful, please use the links to the services below to share it with other readers. You will need a free account with each service to share an item via that service.
Dynamic data visualizations let analysts and business users interact with the data, changing variables or drilling down into data points, and see results in a flash. Advance your use of data visualization with tools that support features like auto-charting, explanatory pop-ups, and mobile sharing.
No doubt your enterprise is amassing loads of data for fact-based decision-making. Hand in hand with all that data comes big computational requirements. Can traditional IT infrastructure handle the increasing number and complexity of your analytical work? Probably not, which is why you need a backend rethink. Big data calls for a high-performance analytics infrastructure, as Fern Halper, a partner at the IT consulting and research firm, Hurwitz & Associates, discusses here.
Redbox's bright-red DVD kiosks are all but ubiquitous these days, located in more than 28,000 spots across the country. Jayson Tipp, Redbox VP of Analytics and CRM, provides an insider's look at how the company has accomplished its phenomenal nine-year growth.
InterContinental Hotels Group (IHG), a seven-brand global hotelier, has woven analytics into the fabric of its operations. David Schmitt, director of performance strategy and planning, shares IHG's analytics story and his lessons learned.
Elizabeth Barth-Thacker, a BI and informatics technology manager at Humana, tells us how her team is creating data transparency and building engagement with the business – with the help of an internal collaboration portal called Humanalytics.
Speaking at SAS Global Forum Executive Conference, Rajeev Kaul, SVP of pricing at OfficeMax, uses a Chinese proverb to explain one of the reasons he's deploying SAS Visual Analytics.
In an All Analytics interview, Mike Cavaretta, technical leader, predictive analytics at Ford Research & Advanced Engineering, shares how big-data is fueling vehicle decisions.
Analytics professionals and SAS executives share how organizations can get on with their work so much faster when working in a high-performance and visual analytics environment.
Analytics professionals who attended SAS's recent Executive Briefing in New York share how they think visual analytics might help their organizations get better value from data.
At Boeing, effective decision making comes down to this simple formula: QxA=E, as executive Jerry Allyne explained at the recent INFORMS analytics conference.
Whether working in major league sports, financial services, or healthcare, analytics, and data, professionals are checking out how visual analytics and high-performance technologies can help them optimize their environments, shrink their cycle times, and improve decision making, as attendees at the recent SAS Executive Briefing in New York share with us.
SAS CEO Jim Goodnight speaks with us at a recent SAS Executive Briefing about getting a feel for what's in your big-data and other new realities powered by advanced analytics.
Jim Davis, SVP and CMO at SAS, talks with us at a recent SAS Executive Briefing about how high-performance analytics and visual analytics take away the concerns over big-data and let companies get down to business with their data.
Tweet This
11 
24 
