Viewers’ emotions central to Médiamétrie’s cinema measurement

Communiqué de presse

For 76% of viewers, cinema is a vector for emotions above all else.* For many years, Médiamétrie has been following viewers’ patterns and has been analysing their experience at the cinema. For the first time in France, Médiamétrie is taking its analyses of viewers’ emotions further, using technology developed by Datakalab. This solution measures emotions expressed by viewers facing a screen while being shown a trailer or a film.

 

Marine Boulanger, Director of Cinema & Entertainment at Médiamétrie explains: “This emotional data supports and provides more detail for viewer data collected by our studies. It provides an even clearer response about the attractiveness and potential of a film, or the effectiveness of a trailer.”

 

Conclusive results

The faces of consenting viewers are filmed, then their attention level and peaks of positive emotions are retranscribed as graphs. This solution highlights the most intense moments experienced by the viewer.

 

In May and June of 2019, Médiamétrie used this approach online to test the trailers of different genres: French comedy, animation and action films. The faces of 900 people were filmed through their computer webcam to record their emotional reactions as they watched a trailer.

Médiamétrie also used this approach for the showing of a French comedy in a Paris cinema.

 

The emotions felt by the viewers during the film and their consistency with the film’s genre are the key pieces of information that allow the field’s professionals to optimise editing and validating of an effective trailer, perfecting its marketing strategy and communications.

 

Marine Boulanger adds: “The battle for attention over video content is growing fiercer. The commercial stakes in film are paramount and it is crucial to offer the best content possible by verifying its effectiveness.”

 

Innovative technology

To implement this initiative, Médiamétrie has partnered with Datakalab, a French braintech start-up specialised in quantifying facial reactions. Deep learning, a branch of artificial intelligence, allows Datakalab to measure the attention and emotions of viewers through cameras set on both sides of the cinema screen.

 

Xavier Fischer, Datakalab Director: “We are delighted with our Médiamétrie partnership. We can already see the value created through the combination of declarative and emotional data. Médiamétrie’s cinema expertise allows us to create the best product for this particular market and to harness our technology in the best way possible."

 

 

 

* Source: Médiamétrie - 2018 Cinema Year - SVoD Barometer January 2019

Please click on the icon to download the comprehensive press release.

Download

Confidence interval calculus

Taille de l'échantillon ou d'une cible dans l'échantillon

n =

Proportion observée dans l'échantillon ou sur une cible dans l'échantillon

p =

%

Attention : ne s'applique qu'à une proportion. Le Taux Moyen est une moyenne de proportions et la Part d'audience un rapport de proportions.
Cet outil est donné à titre indicatif. Il ne saurait pouvoir s'appliquer sans autres précautions à des fins professionnelles.

Test of significance of the differences between two proportions

Permet d'évaluer si la différence entre 2 proportions est significative au seuil de 95%

Proportion

Taille de l'échantillon

Échantillon 1

%

Échantillon 2

%

Attention : ne s'applique qu'à une proportion. Le Taux Moyen est une moyenne de proportions et la Part d'audience un rapport de proportions.
Cet outil est donné à titre indicatif. Il ne saurait pouvoir s'appliquer sans autres précautions à des fins professionnelles.

En complément