Friends engage with social media.

Mining social media to understand what we think about food and drink

The horse meat scandal just won’t go away, which is probably a good thing. At the beginning of last year, it was headline news for good reason, but why are we still talking about it 18 months on?

The reason is simple: we need to ensure it doesn’t happen again. As I said in an earlier blog, the crime in this case was that a nation that does consider the eating of horse meat as taboo was deceived.

What disturbed me most wasn’t the fact that we may have been eating horse meat all along, but the fact that no one told me. I’d like to have a choice over what I eat, so being honest and open about ingredients is top of my list. However, it’s only my opinion. In order to discover what everyone else thought about the horse meat scandal, researchers at Cardiff University have been busy looking at social media engagement from when the news first broke.

By analysing social media data, the researchers will discover public perceptions of the horse meat scandal for the first time, tapping into a rich vein of media coverage that revealed widespread fraud and uncovered the complexity of the UK meat supply chain and the extent of meat imports.

The project will investigate how the growing complexity of international food supply chains is giving rise to a new generation of risks and concerns.

It’s a massive undertaking, but an important one that may change the way we use social media for marketing purposes in all sorts of sectors, whether we’re mining it for positive change or for being able to sell a product in two years’ time.

The University’s Collaborative Online Social Media Observatory (Cosmos, of course) has been awarded an Economic and Social Research Council grant under its Global Food Security Programme (a joint initiative with the Food Standards Agency). The project is in collaboration with NatCen, the University of Warwick and the University of Westminster.

“Cosmos provides a unique opportunity to study the story arc of crises in unprecedented detail,” said computer scientist Dr Pete Burnap. “We have collected data from public Twitter accounts since 2012 and our database of more than three billion tweets will allow us to trace the unfolding of the horse meat scandal, pinpointing moments of escalation, de-escalation and duration.

“We can also mine the data to discover variation in levels of public sentiment and tension around the topic, as well as identify demographic characteristics of those involved and the geographic spread of the scare.

“This study will enhance understanding of the potential of social media analysis to access public perceptions and how these evolve, and to establish how social media analysis can be used in risk governance and engagement with the public about risks more generally.”

I can’t help but imagine a future of such detailed research being undertaken by the food & drink Goliaths of our day. Scratch that; they’re probably already doing it – mining our tweets and posts about flavours, regional trends and packaging choices. It’s not a bad thing. If they have the money to do it, it cascades down to those who can’t afford to do the research, which leads to more innovation and competition.

As Dr Luke Sloan from the Cardiff School of Social Sciences says, “The research will generate new empirical findings on public perceptions of UK food supply chains; what people’s concerns are, what influences these and how they may be best managed in the future.”

If the NSA can mine our data, so can we.

(My thanks to Fil Dunsky for the brilliant illustration used in this article.)