dear UK: more tweets, more votes!!!!
The Oxford Internet Institute reports that Twitter data picked up some of the trends in last week’s election, when traditional polling did poorly. In their blog, they ask – did social media suggest the massive upset from last week? Answer, somewhat:
The data we produced last night produces a mixed picture. We were able to show that the Liberal Democrats were much weaker than the Tories and Labour on Twitter, whilst the SNP were much stronger; we also showed more Wikipedia interest for the Tories than Labour, both things which chime with the overall results. But a simple summing of mention counts per constituency produces a highly inaccurate picture, to say the least (reproduced below): generally understating large parties and overstating small ones. And it’s certainly striking that the clearly greater levels of effort Labour were putting into Twitter did not translate into electoral success: a warning for campaigns which focus solely on the “online” element.
One of the strengths of our original paper on voting and tweets is that we don’t simply look at aggregate social media and votes. That doesn’t work very well. Instead, what works is relative attention. So I would suggest that the Oxford Institute look at one-on-one contests between parties in specific areas and then measure relative attention. In the US, the problem is solved because each Congressional district has a clearly identified GOP and Democratic nominee. The theory is that when you are winning people talk about you more, even the haters. People ignore losers. Thus, the prediction is that relative social media attention is a signal of electoral strength. I would also note that social media is a noisy predictor of electoral strength. In our data, the “Twitter signal” varied wildly in its accuracy. The correlation was definitely there, but some cases were really far off and we discuss why in the paper.
Finally, I have not seen any empirical evidence that online presence is a particularly good tool for political mobilization. Even the Fowler paper in Nature showed that Facebook based recruitment was paltry. So I am not surprised that online outreach failed for Labour.
Bottom: The Oxford Internet Institute should give us a call, we can help you sort it out!
Subscribe to comments with RSS.
Comments are closed.