Emotions run through everything in our everyday life. Your emotions define your mood, and your behavior. When you feel happy, you are more likely to have a good day in the office and enjoy the things you do. It might also make you more receptive to that billboard you saw at the bus stop on your way to work. While being moody or even getting bored while watching an advertisement, chances are you are not very interested in the product, let alone to buy it.
Why emotions are important, and how to get this data?
No wonder researchers, advertisers, and marketers are interested in these emotions. They play a key role in non-verbal communication and are essential to understanding human behavior. It’s for the same reason many marketing conferences are filled with talks about advertisement effectiveness or the most persuasive texts for packaging design.
This general interest in emotions is one of the reasons that facial expression analysis is often used in consumer and behavior research. Emotion data provides crucial insights that allow researchers to explain complex human behaviors in greater depth.
After the fact vs. real-time data
How to get this data? You can always just ask a person. However, it is unlikely to get honest, objective replies. People usually find it very difficult to comment on their own emotions and state-of-mind. Self-reported emotions are not necessarily what a person is actually feeling at that moment. Besides that, asking how someone feels also means you get an ‘after the fact’ reply, while the real-time emotions are what you really want to know.
That’s exactly the reason that facial recognition software like FaceReader makes a valuable addition as a research tool in consumer behavior research, as it helps you to collect objective data in real-time. Based on the original “basic” emotions defined by Paul Ekman¹, FaceReader automatically determines the presence and intensity of Happy, Sad, Angry, Surprised, Scared, Disgusted, and Contempt, as well as Neutral. FaceReader has been validated against human coders², with a degree of agreement ranging from 70% (Disgusted) to 99% (Happy).
This will ensure better understanding of human-human, human-machine, and human-product interactions. And while FaceReader was already able to detect the seven basic emotions, it now can figure out affective attitudes too!
Detecting affective attitudes
Attitudes are dispositions to evaluate objects in a negative or positive way and include three different elements: affective attitudes or evaluations (emotions), cognitions (thoughts and knowledge), and actions (past behaviors or experiences).³
Let’s look closer at affective attitudes: the feelings or emotions that something evokes, e.g. fear, sympathy, or even hate. These complex emotional states differ from the basic emotions described by Ekman [4, 5]. The strength with which an attitude is held is often a good predictor of behavior. The stronger the attitude, the more likely it should affect behavior. So knowing a person’s attitude can help predict their behavior. Valuable information for consumer behavior researchers and marketers, as this can also help with predicting if people will buy a product after seeing an advertisement.
With the new release of FaceReader 7.1, emotions of test participants can be examined even further, as the software is now able to measure three commonly used affective attitudes: 'interest', 'boredom', and 'confusion'. To estimate these Affective Attitudes, the intensities of a number of Action Units are determined. These intensities are combined with other cues, like head shaking and nodding.
FaceReader can estimate the Affective Attitudes Interest, Boredom and Confusion.
These secondary facial affects are available on an experimental basis with the Action Unit Module in FaceReader 7.1, and are more complex than the basic emotions. They are not completely expressed within a single instance, but computed over a window of time.
Knowing if your test participants get bored by watching your advertisement for your new product launch can make all the difference in the success of it.
Not bored yet? Learn more about FaceReader and its new features!
FaceReader methodology white paper
Request the FREE FaceReader methodology note to learn more about facial expression analysis theory.
- Learn what FaceReader is and how it works
- Learn how the calibration works
- Get insight in quality of analysis and output
1.Ekman, P. Friesen, W.V. (1971). Constants across cultures in the face and emotion. Journal of Personality and Social Psychology, 17, 124-129.
2.Terzis, V.; Moridis, Ch. N.; Economides, A.A. (2010). Measuring instant emotions during a self-assessment test: The use of FaceReader. Proceedings of Measuring Behavior 2010, Eindhoven, The Netherlands, 192-193.
3.https://en.wikipedia.org/wiki/Attitude_(psychology) (WP:CC BY-SA)
4.Ekman P. and W. V. Friesen (1978). Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting Psychologists Press, Palo Alto.
5.Ekman P., W. V. Friesen, and J. C. Hager (2002). The Facial Action Coding System. Second edition. Salt Lake City: Research Nexus eBook. London: Weidenfeld & Nicolson (world).