Stim Engine Technology


Stim Engine consists of two technology platforms – Stim Admin and Implicit.

Data Captured

The Stim Admin viewer records very high quality video of participants while they watch “Stims” (stimuli) – video or image media. The video of the participant is then analyzed in two or three key ways:

  • Emotion classification by facial coding
  • Eye-tracking, eye-gaze and visual attention
  • Implicit response testing – we measure the degree of association by the time required to make decisions about concepts

Eye Tracking

Attention is very important. No matter how engaging or persuasive a piece of content, the work put into it is void if people do not notice it.

Eye tracking tells us what content people are paying attention to, and when. It tells us which features are driving emotional responses. It also highlights whether key messaging about brand awareness is being picked up. It is relatively easy to interpret, since it is very objective. Eye tracking is relatively easy to measure, but strongly impacted by task / objective or other internal variables. Robust conclusions can be drawn from relatively small samples (15-30) where the questions being analyzed are relatively simple (e.g. which layout ensures core messaging gets noticed most).


Once a piece of content catches attention, how well does it ‘absorb’ the viewer and cause a psychological response?

Emotions are subtle. We analyze emotions in aggregate because people react to stimuli in different ways; reactions also depend on external factors. Facial coding relies on detection of very subtle signals from small changes in facial expression. For robust insights we prefer somewhat larger samples (30-50). It is also important to note that emotions are not absolute measurements. We focus on significant changes in emotional expression over time, as each individual has a different baseline at any given moment. When looking at something like “brand uplift” we are aiming to capture whether there was an emotional reaction (not everyone will measurably react) and the nature of that reaction. The Emotion Analysis system is designed to capture these effects.

Emotion timeseries


For a brand to grow, it needs to be mentally available and connected to the appropriate purchase / usage triggers in memory.

Implicit and explicit testing (survey) is used to measure viewers’ associations or perceptions of the brand, pre- and post-exposure to the content.

Implicit Testing

This is an optional component. Typically, we measure rapid reaction times at millisecond precision while asking users to make value judgements about words or images. Often, we test before and after exposure to stimuli. The implicit response is easily reduced to a single percentage score which may be incorporated into Emotion Analysis.

Explicit Testing

This is an optional component. Typically, we ask participants to rate content out of 100. There are a number of reasons that these answers may be biased, which is why we use an explicit question as only one part of a more comprehensive analysis of unconscious effects. The explicit response is easily reduced to a single percentage score which may be incorporated into Emotion Analysis.

Aggregation and Segmentation

As already described, emotion analysis is an aggregate analysis – we collectively analyze a group of participants. You can select the group in Stim Engine prior to invoking the analysis. This enables you to analyze different segments of the population and compare the results.