Brainwaves of a few people predict mass audience reaction to TV programs and ads

July 31, 2014

Brain responses of just a few individuals are a remarkably strong predictor of response to future products and messages, according to a study conducted at the City College of New York (CCNY)  and Georgia Tech.

By analyzing the brainwaves of just 16 individuals as they watched mainstream television content, the researchers were able to accurately predict the preferences of large TV audiences — up to 90 percent in the case of Super Bowl commercials. The findings appear in a paper entitled “Audience Preferences Are Predicted by Temporal Reliability of Neural Processing,” published in Nature Communications (open access).

Overcoming bias

“Alternative methods such as self-reports are fraught with problems as people conform their responses to their own values and expectations,” said Jacek Dmochowski, lead author of the paper and a postdoctoral fellow at CCNY at the time the study was being conducted.

However, brain signals measured using electroencephalography (EEG) can, in principle, avoid this shortcoming by providing immediate physiological responses immune to such self-biasing. “Our findings show that these immediate responses are in fact closely tied to the subsequent behavior of the general population,” he added.

Lucas Parra, Herbert Kayser Professor of Biomedical Engineering at CCNY and the paper’s senior author explained: “When two people watch a movie, their brains respond similarly — but only if the video is engaging. Popular shows and commercials draw our attention and make our brainwaves very reliable [and predictable]; the audience is always ‘in-sync.’”

Predicting reactions to TV shows and Super Bowl Ads

In the study, participants watched scenes from The Walking Dead TV show and several commercials from the 2012 and 2013 Super Bowls. EEG electrodes were placed on their heads to capture brain activity. The recorded neural activity was then compared to audience reactions in the general population, using publicly available social media data provided by the Harmony Institute and ratings from USA Today’s Super Bowl Ad Meter.

“Brain activity among our participants watching The Walking Dead predicted 40 percent of the associated Twitter traffic,” said Parra. “When brainwaves  [of participants] were in agreement, the number of tweets tended to increase.” Brainwaves also predicted 60 percent of Nielsen ratings, which measure the size of a TV audience.


Bud Light Commercial – Super Bowl XLVI

The study was even more accurate (90 percent) when comparing preferences for Super Bowl ads. For instance, researchers saw very similar brainwaves from their participants as they watched a 2012 Budweiser commercial that featured a beer-fetching dog. The general public voted the ad as their second favorite that year. The study found little agreement in the brain activity among participants when watching a GoDaddy commercial featuring a kissing couple. It was among the worst rated ads in 2012.

The CCNY researchers collaborated with Matthew Bezdek and Eric Schumacher from Georgia Tech to identify which brain regions are involved and explain the underlying mechanisms. Using functional magnetic resonance imaging (fMRI), they found evidence that brainwaves for engaging ads could be driven by activity in visual, auditory and attention brain areas.

“Interesting ads may draw our attention and cause deeper sensory processing of the content,” said Bezdek, a postdoctoral researcher at Georgia Tech’s School of Psychology.


Abstract of Nature Communications paper

Naturalistic stimuli evoke highly reliable brain activity across viewers. Here we record neural activity from a group of naive individuals while viewing popular, previously-broadcast television content for which the broad audience response is characterized by social media activity and audience ratings. We find that the level of inter-subject correlation in the evoked encephalographic responses predicts the expressions of interest and preference among thousands. Surprisingly, ratings of the larger audience are predicted with greater accuracy than those of the individuals from whom the neural data is obtained. An additional functional magnetic resonance imaging study employing a separate sample of subjects shows that the level of neural reliability evoked by these stimuli covaries with the amount of blood-oxygenation-level-dependent (BOLD) activation in higher-order visual and auditory regions. Our findings suggest that stimuli which we judge favourably may be those to which our brains respond in a stereotypical manner shared by our peers.