BBC to use face-scanning technology to shed light on viewers' tastes

Successful trial of CrowdEmotion enabled the BBC to find how 'how people truly felt about the content they were viewing'

Adam Sherwin
Media Correspondent
Wednesday 10 February 2016 17:42 EST
Comments
The BBC trial divided reactions into six categories: sadness, puzzlement, happiness, fear, rejection and surprise
The BBC trial divided reactions into six categories: sadness, puzzlement, happiness, fear, rejection and surprise

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

The BBC is pressing ahead with plans to utilise new facial coding technology – revealing viewers’ subconscious “emotional attachment” to programmes – after running successful trials.

Developed by a British start-up, CrowdEmotion, the technology uses cameras to record individuals’ expressions and actions.

Facial movements are recorded on a second-by-second basis and the results are divided into six possible emotions: sadness, puzzlement, happiness, fear, rejection and surprise.

The cameras allow researchers to measure the often subconscious responses people have to visual content.

CrowdEmotion is working with the Insight division of BBC Worldwide, the corporation’s commercial wing, on projects which could be used to help the BBC gauge how viewers react to particular programmes.

A pilot experiment, measuring 5,000 people’s conscious and subconscious emotional responses to marketing campaigns on the BBC.com website – from clients including HSBC – has proved a success, BBC Worldwide said.

The BBC wanted to discover if audiences would respond more positively to content which was clearly labelled as originating from a commercial brand.

Facial coding showed a 77 per cent increase in “explicit positivity” towards the brand’s advertising and a 14 per cent increase in “subconscious positivity” when it was clearly marked as sponsored content.

The BBC’s advertising division said the technology “enabled us to find out the emotional response of each person and how they truly felt about the content they were viewing, rather than just relying on traditional analytics such as dwell time and page views”.

A separate BBC Worldwide study with CrowdEmotion installed 200 web cams in homes across the UK, capturing viewer reactions to shows including Sherlock. The BBC said the experiment also produced valuable results.

Further tests have taken place with audiences in Russia and Australia, with responses to around 100 different programmes recorded.

The viewer trial prompted concerns that the BBC would use the webcam technology to “spy” on people’s living rooms and assess how diligently they were watching programmes. But the BBC believes facial coding will help it to serve audiences merely by gaining a greater understanding of their tastes.

Rather than tailoring new programmes to match the results of the experiment, the insights would be used to guide viewers towards more shows they might like, informed by their conscious and subconscious reactions.

CrowdEmotion, supported by the BBC Worldwide Labs programme, aims to become the largest dedicated facial coding provider in the world. The BBC programmes trial gave the company a data set of 10,000 “face videos”.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in