What Makes Great Advertising: Lessons From Language

Orlando Wood, MD BrainJuicer Labs, writes about an experiment in language analysis in partnership with Relative Insight.

One of the main barriers to the uptake of social insight has been that behind the attractive dashboards and metrics lurks a great deal of hard human work. People have been required to build dictionaries, update vocabulary lists, and check output. And that’s in addition to their analysing the output and turning it into useful insight.

One company that might be able to offer a solution to the analysis of large amounts of text data is Relative Insight. BrainJuicer Labs met up with them to understand how the software they’ve developed might help us to interrogate the language respondents use in large text datasets.

Relative Insight has its origins in software used to detect criminal intent in online posts. It can detect from a person’s use of language, for instance, whether they genuinely are a 10 year old girl, or in fact someone much older, pretending to be a 10 year old girl. It does this by comparing two bodies of text and looking for subtle differences in the use of words, grammar or themes. Without you realising, your language says a lot about you.

We wanted to see whether this approach could tell us anything about how different audiences respond to advertising and, indeed, whether it could help us to understand what makes great emotional advertising. We know there is a direct relationship between emotional response to advertising and its in-market efficiency, so we asked Relative Insight to analyse open-ended text responses detailing how people felt towards 150+ ads we had recently tested. The ads were part of our FeelMore50 testing – a body of creative work that has been awarded for its creativity or achieved viral success.

6 Fascinating Ideas From The Connected World Conference

Last Friday the MRS held its first Connected World conference – a social media research event with a difference. Though the attendees were social media researchers and clients, the speakers were almost entirely drawn from outside the research business. In fact, BrainJuicer were one of only two research agencies represented – the other were social specialists FACE – on a panel about how to “cut through the noise” in social media research.

But for the most part, research took a welcome back seat, quit its yapping about disruption and transformation, and listened for once. Marketers, psychologists, fandom experts, designers and comedians took the stage for a conference centering on inspiration and shared knowledge, not just trotting out the latest case study.

With that in mind, here’s my pick for the six most interesting things I learned at Connected World.

So, How Many Basic Emotions Are There Again?

We’ve had this article (or variants of it) brought to our attention a lot in the last couple of weeks. It’s about some new research by academic Rachael Jack which calls into question Paul Ekman’s idea that there are only “six basic emotions”. According to Jack’s work, there are actually four.

This has got a lot of press. People are really interested in the idea that there are common emotions that work across cultures – it’s a reason our FaceTrace methodology, which measures emotions and uses Ekman’s model, has been such a success. 3 million people have used FaceTrace 5 million times in 75 countries, so we know it works – but what if Ekman was wrong?

NGMR Disruptive Innovator 2013

We at BrainJuicer are thrilled to bits that Chief Juicer John Kearon won the prestigious NGMR Disruptive Innovation award, announced today at The Market Research Event 2013.

This is the third time we’ve been recognised for innovation in the last few years – we also topped the GRIT survey of innovative research firms in 2010 and 2011 – and it means an awful lot. Especially since, quite frankly, the competition to be innovative in market research is fearsomely tough right now, and getting tougher all the time. This is not your parents’ research industry – it’s not even your older sibling’s.

Fortune Favours The Brave

Our Adventures At IIeX Philadelphia

The research conference calendar is a crowded one, so we approached last week’s IIeX event in Philadelphia with goodwill and scepticism. Goodwill because Lenny Murphy, who organised it for Greenbook, is a tireless champion of the new in research. Scepticism because how new could a conference dominated by suppliers possibly be?

Pretty new!

There was – as expected – some whiz-bang technology. A Zoomkube kiosk – displaying live searches by attendees – and a Bizzabo app replaced the standard conference programme, setting the tone: no quarter given to attendees just wanting what they were used to.

But the thrust of the conference wasn’t so much new tech as a statement of intent: the old dogmas are dying.

MROCs: The Long And The Short Of It

When MROCs – Market Research Online Communities – were first invented, they mirrored the way online communities worked. They were very much like web forums: big, long-running, semi-permanent structures with hard-working moderators whose participants dropped in and out at leisure.

The main difference was how quiet a lot of MROCs felt. In an environment where getting 20 minutes input a week from a participant was a success, it’s no surprise most communities seemed somewhat empty. And no wonder. MROCs bore the same relationship to functioning web communities as a movie set does to a real place. Devoid of life until the director turns up and says “action!”.

Aaaand… discuss!

For a while people made efforts to change this – to make research communities more vibrant or more engaging. But it didn’t solve the problem.

10 Things We Learned About Big Data At The Analytics With Purpose Conference

Over the last two days in San Diego, BrainJuicer has been proud to co-present the first Analytics With Purpose conference with the AMA. The subtitle – The Human Edge Of Data – was a pointer to the fact that we both wanted this to be more than “just another Big Data conference”, but instead present a panorama of the complex relationships between marketing, research, people and large-scale data. In this post conference Chair Tom Ewing looks back on the event and pulls out 10 talking points.

A panorama of the conference by John Szabo

In her opening keynote at Analytics With Purpoise, IBM’s Elana Anderson outlined the essential problem – and opportunity – confronting marketers in an age of big data: the challenge of individual engagement at scale. With such vast and deep knowledge of people’s behaviour, interaction and interests, where are the ways to practically use it? Over the course of two days in San Diego, I can’t pretend we solved the problem but we explored a few pathways and had fun doing so.

The next ten paragraphs are a summary with a difference for a conference with a difference – a series of soundbites which sum up the event and spotlight some of its themes. If it makes you wish you were there – well, that’s the idea, and keep an eye open for sequel events!

Research And Big Data: 7 Roads To Enlightenment

In a couple of weeks BrainJuicer’s Tom Ewing will be flying out to San Diego to chair the American Marketing Association’s newest conference. Analytics With Purpose: The Human Edge of Big Data will offer a practical tour of the issues arising as market research meets “big data”. In this post Tom outlines the themes of the conference.

Some people might tell you that research getting to grips with big data is like a shrew getting to grips with a sumo wrestler – as Phil Rance of Quadrangle once tweeted, “Research is a pimple on the arse of big data.”

What I’ve seen, though, both from working on this conference and looking at others, is that plenty of big data practitioners are more than happy to break bread with researchers and think through how we can work together. And from the client side, as ever it’s practicality and results that win out over method. True, research might not have a role to play in areas where companies are using large-scale data – but if the speakers at San Diego (which include IBM, Coke, Hyundai, Google, Getty and many more) are any guide, they’re not ruling it out either.

An early big data pioneer, by Stan Lee and Jack Kirby

While I was helping work out the line-up for the conference I started making notes on the key themes coming out of the conversations I was having – outlining the questions and ideas I was most excited to see emerging. For the benefit of people who can’t attend, I’ve blogged them here – seven themes in big data, from a researcher’s point of view.

Brian’s Grab Bag: The Wild New World Of Retail

Every so often I like to just put up a few links to great ideas the BrainJuicer team have bumped into online. This post’s theme is retail.

An awful lot of retail innovation right now involves managing the fallout from the digital shopping revolution. Lucy Jones of the Financial Times may have nominated “phygital” among her worst words of 2012 – can’t say I blame her – but the mix of physical and digital doesn’t need a portmanteau to matter. Innovation blog PSFK spotlighted two interesting developments recently – PayPal and QR-code driven vending machines in Singapore, and more radically ‘virtual supermarkets’ in China: augmented reality shops where your virtual selections become real deliveries.

PayPal vending machines, from PSFK.

For once-mighty brands who’ve found themselves disrupted by start-ups, retail might offer an unlikely route to salvation. Polaroid, for instance – whose newest idea is fotobars where you can print super-premium copies (on anything from picture stock to bamboo!) of your digital photos. For such brands the experience is King.

Other brands want to enhance their physical experience too. Nissan, for instance, is exploring the idea of a brand smell in its showrooms. Don’t laugh, it sounds rather a nice smell – and at BrainJuicer we’ve learned that scent can pack a big punch in sales terms.

Away from such rarefied concerns the big boys of retail are still mass market stores selling to a mass of consumers. And when you get people together, things can get a little vexed – an upcoming paper in the Journal of Consumer Research explores what happens when customers break social norms. “Consumer to consumer punishment decisions”, they call it – whether people get called out for queue jumping or spilling goods. It’s a jungle out there, people: shop safely.

Consumer behavior in a retail environment isn’t always so wild, but it is often “irrational” and understanding it can help your store or brand thrive. Next Wednesday, Will Leach of BrainJuicer Behavioral Labs is giving a free webinar exploring shopper insights in a world of behavioral economics. I’ll be blogging more about that on Monday but here’s a link if you want to register right now.

In the meantime, happy reading, and enjoy your weekends!

The Top Experiments of 2012

Last month we ran the “Advent Calendar of Experiments” – 24 things we in BrainJuicer Labs ran or helped run last year. Here’s the “Master List” of experiments so you can go back and check out the ones you missed.

BEHAVIOUR AND DECISION MAKING

• Understanding how visceral physical states affect in-store behaviour. (No. 1)
• Testing the demographics of “system 1” and “system 2” responses. (No. 2)
• Using pressure and distractions to make pack testing better. (No. 11)
• Exploring how emotion influences online behaviour. (No. 19)
• Using scent to prime decision making in stores. (No. 20)
• Investigating ‘regulatory focus’ and its effect on choices. (No. 23)

ADVERTISING, VIRALITY AND SHARING

• Finding out what makes ads go viral. (No. 3)
• Looking at the effect of interactivity on ad effectiveness and viral potential. (No. 6)
• Working out what drives long-term business effects of ads. (No. 8)
• Analysing Olympic advertising and sponsorship effects. (No. 10)
• Demonstrating the benefits of sharing: shared ads feel better. (No. 12)
• Understanding the use of extreme negative emotions in viral ads. (No. 16)
• Proving the power of emotional images in print ads. (No. 17)
• Exploring the success of Kony 2012 (No. 21)

PREDICTIVE MARKETS

• Validating predictive markets in-store. (No. 14)
• Running a predictive market project in under 24 hours. (No. 18)
• Predicting the winning Christmas toy of 2012 (No. 24)

COMMUNITIES AND ETHNOGRAPHY

• Using games to explore “we”-research in communities. (No. 4)
• Exploring audio, sound and self-narration as ethnographic tools. (No. 5)
• Using the “Telephone” game to explore word-of-mouth for new concepts. (No. 7)
• Using friendship pairs in mobile ethnography (No. 22)

GENERAL COOL STUFF

• Using “second screening” as a research tool. (No. 9)
• Tracking the emotional appeal of brands against their share price. (No. 13)
• Using A/B testing to check survey wording. (No. 15)