Can you predict what people are thinking based on analysis of online debate?

by Stephen Tall on August 1, 2010

That’s the question a company called, somewhat improbably, Onalytica have set out to answer in their paper, Using the Internet as a Market Research Database.

They’ve summarised their key findngs thus:

1. Changes in daily election poll results could be estimated by measuring the changes in the relative amount of online discussion
2. We find that ‘traditional media’ maintains a high level of influence, and that the influence of ‘social media’ was small
3. The Lib Dem’s performance was similar to that of a new brand entering an established market place
4. Labour and the Conservatives had a joint interest in preventing discussion of the Lib Dem’s
5. ‘Bigot gate’ surprisingly hurt Nick Clegg a lot – not just Gordon Brown
6. Gordon Brown was unpopular; and changing sentiment towards him during the campaign was correlated with Labour performance

Much of this comes under the catageory ‘as expected’. Point number 5 did, however, interest me – that the switch of attention on the leaders away from Nick Clegg to Gordon Brown was a major reason why the Lib Dems’ campaign lost traction in the last week.

It’s sort of counter-intuitive – most of us at the time assumed that the then Labour leader’s labelling of one of his voters, Gillian Duffy, as a ‘bigot’ would torpedo his party’s campaign. However, Onalytica assert that the Lib Dems and Nick Clegg suffered from the limelight moving on, and never recovered. I still find it more likely that a combination of media focus on the prospects of a hung parliament, and the drip-drip impact of the right-wing attacks on Nick personally were bigger issues – but it’s an interesting alternative hypothesis.

Another interesting assessment is the verdict that Nick Clegg’s brand was not closely associated enough with the Lib Dems for the party to benefit from his increased popularity:

… the success of the Clegg product did not translate into equal success for the Lib
Dem’s brand. … from 6th April until 6th May, there was always more influential debate on Nick Clegg compared to his peers, or than there was for the Lib Dem’s compared to Labour and the Conservatives. Relative to David Cameron and Gordon Brown, Nick Clegg’s Share-of-Influence increased from 20% on the day before the first televised debate to 35% one day after. However, the increase for the Lib Dem’s (relative to the Conservatives and Labour) was not as significant rising from 11% to only 17% over the same period.

This discrepancy suggests that Nick Clegg was not tightly associated with his brand. The data lends support to the notion that if the party had taken action to align the brand further with their leader, it is not inconceivable that overall performance could have been improved.

Again, this may not surprise: after all, over three debates many voters felt they had got to know Nick. But it’s much more difficult to know a political party that’s not been in power for 80 years in the same way. Similarly, David Cameron’s ‘brand’ has nearly always out-polled the Conservative ‘product’.

That the Lib Dems were not tightly associated enough with their leader is an interesting counter-point, though, to the Liberator thesis (which to an extent I share) that the party made a mistake by focusing on Nick Clegg and ditching the ‘joint ticket’ of Nick and Vince Cable which the party had been building for the previous two years. Though it might be added that Vince’s brand identity with the Lib Dems is, I suspect, weaker even than Nick’s.

Finally, there’s a table I can’t resist producing. I don’t understand its methodology or scoring (or therefore its credibility), but as it shows Lib Dem Voice as among the 20 most influential sites in the UK general election 2010 I produce it for posterity regardless:

Though the Caledonian Mercury wins it for me ever time :)

One comment

New post: Can you predict what people are thinking based on analysis of online debate?

by Stephen Tall on August 1, 2010 at 10:36 am. Reply #

Leave your comment


Required. Not published.

If you have one.