CMO Guide For Measuring Attention: Facial Coding

But measuring attention is not trivial. And that's why we published our latest report, "The CMO Guide for Measuring and Managing to Attention Outcomes.” 

We recently covered our guide's fourth chapter on Brain Scans and EEGs. Now let’s cover the next topic of our next chapter: Facial Coding.  

While we’ve attempted to provide a neutral summary of the attention metrics landscape, we (the Realeyes team) are closest to facial coding due to our 10 years of R&D, multiple patents and happy cilents. 😊  

The emergence of Attention AI enables both the measurement and management attention outcomes.  

While still early, attention AI is proving to scale in a cost-effective manner. It is natural, observational, proving to be reliable and predictive of attention and other real-world outcomes.  

This technique uses computer vision and machine learning to apply the decades-proven science of psychology and facial coding. It relies on opt-in viewers to enable their device cameras to anonymously detect their facial cues and capture response second by second, frame by frame. 

Attention AI is applicable both in measuring the attention-earning potential of creative in forced-exposure testing situations, as well as in live in-context situations like watching movies, app usage, gaming and website browsing. The precision and granularity of attention and emotion AI is powerful for developing marketing models that predict real-world outcomes (like video completion rates and social sharing), as well as attentiveness. 

While attention is what enables a media or brand experience to enter a person’s consciousness, it is emotion that controls attention and creates memorability. This intelligence unlocks clear prescription to measure and optimize creative, media and audience for attention outcomes -- far beyond crude A/B testing frameworks. 

Finally, attention and emotion AI is privacy safe by design, and it is not the controversial practice of facial recognition.