Pre-testing of TV commercials by having focus groups evaluate various storyboards is common practice, given the considerable costs of airing commercials and the need to allocate a marketing budget to the most effective campaign. Functional MRI -based neuromarketing allows us to by-pass focus groups, surveys and other traditional market research methods, making better and more reliable predictions of effectivity. For instance, it has been shown that the effectiveness of anti-smoking campaigns is predicted better by brain scans than by the opinions of marketing experts (Falk et al 2012).
At Neurensics we have shown that the effectiveness of TV commercials (measured by Effie award-winning TVCs) can be predicted with over 80% accuracy using fMRI -based technology (Lamme & Scholte 2013). Huge sums of money can be saved in airing costs by this kind of testing. Even so, it remains problematic having to conclude that a TV commercial is better not aired after the high costs of production have been incurred. However, if guided by neuromarketing expertise it would still be possible to alter a commercial post-production, by re-editing, changing music, voiceovers, etc. It would be even more helpful to have a tool that allows the effectiveness to be tested prior to production.
Reverse engineering of storyboards from TV commercials
Ideas for TV commercials are often pitched in the form of a storyboard. A sequence of images is drawn, accompanied by a brief story explaining the general idea or concept. We tested to what extent these kinds of storyboards resemble the brain activation of the final TVC, and therefore whether they can be used to predict the final TVC’s effectiveness. Twelve TV commercials were sketched back into storyboard format in a systematic manner: key shots of the TV commercial were transformed into cartoon drawings, typically 10 shots per commercial. A (male) voice-over was used to explain the story of the commercial, reading the final packshot message aloud. The drawings and voice-over were compiled into a slide show with the same length as the original commercial.
While lying in the MRI scanner, subjects viewed the storyboards followed by the actual commercials. To evaluate TVCs we use a proprietary method where we record activity from 13 neural networks, representing a typical (largely unconscious) emotion or brain valuation. These emotions (mappers) are grouped into four clusters: positive emotions, negative emotions, personal appeal, and general impact. Our previous research shows that the balance between positive and negative emotions is most indicative of TV commercial effectiveness. We correlate the mapper values obtained for a storyboard with those obtained for the actual commercial, to test to what extent storyboards have any predictive value for the neural impact of TVCs.
The example illustrates the principle of analysis. Both storyboard and TV commercials evoke fairly similar (but not identical) mapper values. Note for example, how negative emotions are generally higher than positive emotions. This similarity can be expressed in the correlation value, which in this case is 0.76. A value of 1.0 would indicate perfect similarity.
TV commercials can be predicted from their storyboards
In the sample of commercials and storyboards that we tested, we found cases of fairly high and low correlation, but never negative correlations. On average, the correlation value is 0.35. This value is comparable to the correlation value of 0.37 that is obtained when each individual value of the TV commercial is plotted against the value obtained for the storyboard. Statistically, the correlation is highly significant (p = 0.0004). These results indicate something very important: relatively simple images and narrative of storyboards have a reliable predictive value for the neural impact that TVCs will have if made according to these storyboards.
In evaluating our results, we found that not all mappers are equally predictive. For some mappers (such as attention) there is a very high correlation. In others, however, the correlation is low. An obvious way of improving predictive value is to collapse emotions to their main axes (positive emotions, negative emotions, personal appeal and general impact). At the level of the main axes, storyboard values correlate very significantly with TVC values (R = 0.48, p = 0.002). This shows that our method is very well suited to evaluate the future pos-neg balance of a commercial, with a correlation of up to 0.64 (p = 0.03). And as we have seen in the Effie study (Lamme & Scholte 2013), the balance between positive and negative emotions is a highly accurate predictor (over 80%) for a commercial’s ability to evoke sales intention.
Concept (left) vs Final (right)
This study has proven that fMRI technology is very suitable for the evaluation of a commercial, prior to production. We found two levels of predictive value in the study. On the level of the 13 emotions, pretesting in this manner helps to prevent mistakes by avoiding emotions that have a negative impact on the effectiveness of the TVC. At the level of the main axes, the tool predicts the ability to evoke sales intention. In making TV commercials, fMRI-based storyboard testing is therefore a very cost-effective and reliable tool to predict the most successful course of action, early on.
We found that even a very simple storyboard can predict the neural impact of a TV commercial. This tool is most suited to compare different TVC proposals when a decision needs to be made about which of these will result in the highest conversion. We propose that storyboards are made relatively early on, and tested for their effectiveness in influencing consumer behavior already in the conceptual stage. For the first time, a tool is available that can change the advertising industry. No longer do we need to wait for a commercial to work. We will now know this in advance.