Emotion Measurement

Test and evaluate the emotional potential of your content

How to analyse the emotions of cinemagoers during a film or its trailer

With increasing competition in the paid-for video field, it is a challenge to stand out and to tempt people to watch from the moment they see the trailer. To make a film stand out and make a lasting impression, it is paramount to have content that has strong emotional involvement to make an impact. It therefore becomes important to have indicators to measure a content's emotional engagement.

So much key information supports existing devices in terms of optimising editing, choosing how to create a video or even fine-tuning the marketing strategy or communication levers.

The Emotion Measurement study evaluates and qualifies the emotions of viewers.

  • Verify viewers' level of attention and its evolution
  • Validate the real presence of emotions, the moment of their arrival, their level, their type
  • Confirm the strongest moments and the triggering elements
  • Cross-check the measured emotion with the one that was stated, validating the expressed intentions

The Emotion Measurement study's target are 18-year-old viewers and involves content such as films, series, TV programmes, trailers and advertisements. It is conducted in three stages:

  • Capturing emotional reactions as content is viewed
  • Recording all answers given during questioning about the content
  • Comparison of the two sources of information

To implement this initiative, Médiamétrie contacted Datakalab, a French start-up specialised in quantification of facial reactions. Datakalab uses Deep Learning (AI) to measure viewers' attention and emotion by recording them via their webcam or with cameras in the cinema.

Four key indicators were compiled in partnership with Datakalab: attention, presence of emotions, positive emotion and divergent emotion.

Customised study and systems

  • In the cinema: during a test projection for a long format (film, series, etc.)
  • Online: during a short-format test (trailers, teasers, film ads, etc.)

Confidence interval calculus

Sample size or target in the sample

n =

Proportion observed in the sample or on a target in the sample

p =

%

Warning: only applies to a proportion. The Average Rate is an average of proportions and the Audience Share a ratio of proportions. This tool is provided for information purposes. It cannot be applied for professional purposes without further precautions.

Test of significance of the differences between two proportions

Used to assess whether the difference between 2 proportions is significant at the 95% threshold

Proportion

Sample size

1st sample

%

2nd sample

%

Warning: only applies to a proportion. The Average Rate is an average of proportions and the Audience Share a ratio of proportions. This tool is provided for information purposes. It cannot be applied for professional purposes without further precautions.

Linked solutions
More