In our work, we attach great importance to reliability and scientific evidence. Here, you can read about the key scientific studies which indicate that facial expressions and emotions are valuable in predicting sales and consumer decisions.
Our team of psychologists and experts in artificial intelligence will be happy to answer your questions about the scientific foundations of Ellen.`We also recommend reading our FAQ, where we have given answers to key questions about the Ellen system.
Look how we connected psychology and technology. Download elaborated by Quantum Lab WHITE PAPER
Emotional ads are much more effective than rational content, especially in the long perspective. They generate twice as much profit and can sustain it much longer than a rational message Binet, L., Field, P. (2013). The long and the short of it: 10 key principles of success. Raport Instytutu Praktyków Reklamy (IPA).
Customers who feel an emotional connection to the brand are on average 52% more valuable income-wise compared to customers that are merely satisfied. Magids, S., Zorfas, A., Leemon, D. (2015). The New Science of Customer Emotions. In: Harvard Business Review. Noweber, 2015
New empirical data shows that emotional advertising model and measuring the contents emotional response, lead to greater efficiency, effectiveness, better planning and decision-making during content design. Wood, O., Using an emotional model to improve the measurement of advertising effectiveness. BrainJuicer.
The Millward Brown study showed that the more emotions appear in the ad, the better the ad is remembered and the greater consumer involvement it generates, which in turn translates into more sales. Brown, M., (2009). Should My Advertising Stimulate an Emotional Response? Millward Brown: Knowledge Point.
Research on consumer facial expressions shows that the analysis of the time when/how long consumers smile while watching advertisements allows you to specify the extent to which they like the ad and want to see it again. McDuff, D., Kaliouby, R., Senechal, T., Demirdjian, D., and Picard, R. (2014). Automatic measurement of ad preferences from facial responses gathered over the internet. Image and Vision Computing, 32, 630-640.
The results of the current studies indicate the role of anxiety in creating an emotional attachment to the brand. The researchers suggest that in case of that response association with the brand can be positive. DUNN, L., HOEGG, J., (2014). The Impact of Fear on Emotional Brand Attachment In: Journal of Consumer Research. June 2014, Vol. 41 Issue 1, p152-168
Research shows that the key to effective content virality is emotional engagement. It turns out that content that triggers high emotional engagement is more likely to be shared. Berger, J., Milkman, K. (2012). What Makes online Content Viral? Journal of Marketing Research, Vol. 49, No. 2, pp. 192-205.
Ads that trigger positive and negative emotions in an alternating sequence are especially effective. Mileti, A., Prete, I., Guido, G. (2013). Brand Emotional Credibility: Effects Of Mixed Emotions About Branded Products With Varying Credibility. In: Psychological Reports. Oct2013, Vol. 113 Issue 2, p404-419. 16p.
Studies have shown that the emotions of surprise and joy focus consumers’ attention on the ad for longer and therefore make them stay in front of a computer screen for longer. Teixeira, T., Wedel, M., and Pieters, R. (2012). Emotion-induced engagement in internet video ads. Journal of Marketing Research, Vol. 49, No. 2, pp. 144-159.
The analysis of more than 12,000 facial expressions has showed that it is possible to use them in order to predict the extent to which consumers will like the ad and will be willing to buy the product it advertises. McDuff, D., El Kalioubi, R., Cohn, J. F., & Picard, R. (Accepted with revisions). Predicting ad liking and purchase intent: Large-scale analysis of facial responses to ads. IEEE Transactions on Affective Computing.
It is easier to remember and recall content that evokes strong emotional arousal. Bradley, M. M., Greenwald, M. K., Petry, M. C., Lang, P. J. (1992). Remembering pictures: Pleasure and arousal in memory. Journal of Experimental Psychology: Learning, Memory, & Cognition 18 (2): 379–390.
Body language (gestures, facial expressions, body posture, touch, distance, smell, eye contact), makes up over 60% of the statement that you communicate while interacting with other people. Nonverbal communication in primates
Microexpressions are short (about 50 ms), are not subject to conscious control and are a revealing sign of the persons underlying emotions. Throughout the world, they are expressed in the same way as described by Darwin in 1872. Darwin, C. (1872). The Expression of the Emotions in Man and Animals. London: John Murray.
In 1978 Paul Ekman and William Friesen published a classification of facial muscle movements known as the Facial Action Coding System (FACS). Systematization of facial muscle movements made it possible to precisely define and encode facial expression accompanying emotions.
Facial Action Coding System (FACS) and the FACS Manual". Face-and-emotion.com.
Research on emotions and their combination with expressions were started by Paul Ekman in the 60s. He found and documented facial expressions that accompany emotions in every human culture. Ekman, P. (1992). Are There Basic Emotions? Psychological Review, 99(3), 550-553.
What are emotions? Research shows that emotions are present in every aspect of our lives. They dictate our actions and our response to their consequences. Are there universal patterns that can support the decisions we make on a daily basis? Ekman, P. (2016). What Scientists Who Study Emotion Agree About, 11(1), 31-34.
A Convolutional Neural Network (CNN) is a type of artificial neural network in which the pattern of connections between the neurons imitates the organization of the visual cortex in animals.
Dan, C., Meier, U., Masci, J., Gambardella, L., Schmidhuber, J., (2011). Flexible, High Performance Convolutional Neural Networks for Image Classification. Proceedings of the Twenty Second international joint conference on Artificial Intelligence Volume Volume Two 2: 1237–1242.
Retrieved 17 November 2013.
Different kinds of microexpressions can be measured by combining different facial geometry models, facial texture models or hybrid appearance models. Sumathi, C.P., Santhanam, T., Mahadevi, M. (2012) Automatic facial expression analysis a survey. International Journal of Computer Science & Engineering Survey (IJCSES) Vol.3, No.6, December 2012.
The methodology is rich in tools for detecting microexpressions in videos. By clicking the link, you can retrace the history of facial expression reading techniques used in computer programs. Cohen, N. Sebe, A. Garg, L. Chen, and T.S. Huang, (2003) Facial expression recognition from video sequences: Temporal and static modeling. Computer Vision and Image Understanding, 91(1- 2):160–187.
Apart from the current emotional state, can computers reveal hidden agendas? Based on facial microexpressions, we can find out if our interlocutor is trying to deceive us. Tsiamyrtzis, P., Dowdall, J., Shastri, D., Pavlidis, I. T., Frank, M. G., & Ekman, P. (2007). Imaging Facial Physiology for the Detection of Deceit. Internetional Journal of Computer Vision, 71(2), 197-214.