Mood for thought

There is a radio station in Ireland that kicks off its afternoon drive time program with the presenter waffling on about a daily ‘happiness index’. I always thought this was a bit bland and a gimmick. After all, who keeps or compiles this happiness index and how could it possibly mean anything?

I then read something which put me thinking. Researchers at the University of Manchester and Indiana University have put some science behind this idea of  ‘sentiment tracking’.

They looked at how global emotion and mood, as measured via something like Twitter, could predict stock market activity. They investigated whether measurements of collective mood states derived from large scale Twitter feeds, correlated to the value of the Dow Jones Industrial Average (DJIA) over time. They analyzed the text content of daily Twitter feeds by two mood tracking tools, OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS)

Their results indicated that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions. If you want to predict closing prices on the Dow Jones, have an eye on the Twitter feed.

This raises some interesting questions about how we look at social media data or activity. It may justify a more qualitative approach. When it comes to social media marketing, we may need to look at how our followers feel, rather than just counting them. 

This type of index should make us stop and think about how we interpret the holy grail of Big Data. Does this happiness index change with the weather?, with a regions sporting success? and if so does that affect stock markets or consumer spending? Which is cause and which is effect? Plenty for the self proclaimed big data scientists to ponder there. 

Wish you were here

I came across an interesting BPS Research Digest post which looked at a study by Belgian psychologist Saartje Cromheecke.

Working with a Belgian technology company Cromheecke’s  team sent out a real job opportunity to 1,997 potential applicants. Half got the standard email we all see every day and the other half got a hand-written postcard showing a coffee mug and a blank daily agenda. The email and postcard message featured the same layout and included the same written information and content about the job vacancy. Both type of applicants now had the same chance to apply.

Over all 62 of the those contacted applied for the job. But 82% of them had received the postcard, just 18% had received the email. Put another way, only 1% of those emailed actually applied for the job compared with 5% of those who received a postcard. Follow up research also suggested that respondents to the postcard tended to be better educated, consistent with the researchers' prediction that a recruitment message sent via a "strange" medium will be more likely to grab the attention of better-qualified personnel who aren't actively looking for new opportunities.

The BPS post does make the important point that Cromheecke's team aren't saying that postcards will always be the answer. Rather, "this field experiment puts forth 'media strangeness' as a more general evidence-based principle, which recruiters might take into account when selecting media for communicating job postings."

Recruitment aside, this could also play a role in other customer or client contact situations. Would potential targets respond better to a postcard or some other ‘strange media’ than an email? Would you be better off sending a special offer on a cup, coaster, postcard? The ‘strange media’ does not have to be the last word in graphic design, it just has to be different and convey the necessary information.

If you get the time, try it out. For the price of a few postcards you could see the improved response levels Cromheecke's team did. If they relied on email, they would have had nothing like 62 candidates to choose from.