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.