Millennials are increasingly choosing to engage with organisations through visual means and there is an abundance of apps that enable them to post, share and like digital material of whatever they consider to be the hot topic of the day. These photos, videos and other images not only record the moment in time but also have the potential to capture attitude, feelings and behaviour. It’s hardly surprising therefore that marketers are exploring different ways to gather, monitor and evaluate this unstructured feedback in order to secure and maintain high response rates and take a more innovative approach to customer feedback.

In regions such as South East Asia, where internet coverage is poor but mobile (and more importantly smart phone) ownership is high, providing the ability to share feedback in the form of lifestyle studies is already well established. In a bid to develop highly tailored marketing and sales programmes for specific geographic areas, marketers have combined multimedia diaries with GPS/location-based data to create real-time (photo, video, audio) profiles of individual consumer buying habits. Respondents answer short surveys, provide video demonstrations, and photograph their homes or favourite objects to provide the research team and brands with a very personal picture of where they live and what makes them happy. This enables marketers to tailor marketing programmes to the nth degree.

Perhaps the most exciting application of the digital image is the use of facial and emotion recognition technology. This is now starting to be explored by the Market Research industry and will no doubt make its presence increasingly felt in customer experience and Voice of the Customer programmes.

Facial expressions are strongly linked to emotions, and therefore attitude, which is why research organisations have worked so hard to assess and incorporate emotional response into research studies for so long. However using human observation of recorded videos to try to gauge emotional response can be limited by unintended observer bias, amongst other things.

And this is where facial expression recognition technology comes in. Its ability to record even the most fleeting of facial movements that correspond to emotions, typically based on the human-observed system called FACS (Facial Action Coding System), offers the potential to deliver a much greater level of insight about personal sentiment and reactions.

It uses machine-learning algorithms to build a huge reference database of expressions against which to judge the face being viewed: not dissimilar to the way text analytics systems “learn” how to categorise particular words, phrases and verbal expressions. With that database in place – and built upon with every usage – facial and emotion recognition solutions offer a scalable, repeatable and consistent way to capture emotions.

So in the year that customer experience leaders have declared “The Year of Emotion”, it makes sense to harness this new technology to find out how emotions are driving spending and loyalty at the point of experience. This knowledge will not only give researchers a greater understanding of behavioural patterns but can also help to predict likely future consumer actions. This will in turn help brands to make better business decisions about product and service offerings and the overall customer experience.

Initial applications are likely to be niche or very specific in nature, such as ad testing where a respondent’s webcam will record their reaction to an advert as part of a wider survey. The technology is already in use by a number of leading firms who’ve been able to refine their advertising campaigns according to respondents’ reactions to test adverts. Not only does this enable marketing teams to create the most effective adverts possible, it’s an ideal tool for localising content for global campaigns by understanding precise elements that resonate – or alienate – a particular market.

That said, it is fair to say that people from different nationalities and cultures have different levels of emotional response, and different facial structures, so benchmark data will need to take this into account.

And while many people are now used to engaging with video content through a variety of media, including mobile phones and tablets, respondents must be in a position where their camera is capturing their expressions clearly. Any loss in clarity due to lighting levels or viewing angles will hinder the technology’s ability to read critical expressions.

Privacy will also be an issue for some, most likely an older demographic that may not be prepared to provide their permission for you to access their webcam.

However it’s clear that emotion detection and its ability to leverage digital images will be a valuable addition to the Market Research arsenal. It may very well be incorporated in broader surveys in the first instance but an accuracy rate of around 95% is sure to encourage new and exciting applications of the software. Some will fly and some may pass by the wayside but either way, are you ready for your close up?


By Karine Del Moro, vice president of marketing at Confirmit


Want to keep up with the latest ideas in digital marketing? Free conference and exhibition Integrated Live is the place to be.

PrivSec Conferences will bring together leading speakers and experts from privacy and security to deliver compelling content via solo presentations, panel discussions, debates, roundtables and workshops.
For more information on upcoming events, visit the website.

comments powered by Disqus