M vs Microsoft Episodes 16
Can AI Platform Identify Human Flirting ?
Flirting is an action that demonstrates a romantic interest in someone and signals the purpose of getting attention from another person. When people flirt, they tend to show their most attractive sides, both internally and externally. Flirting is ubiquitous in our lives, so let’s explore the science of flirting.
When people flirt, there are 2 main emotions come into play: happiness, high self-esteem which can be described as positive contempt. When people see an attractive person, they will be surprised initially and then become happy immediately; however, there is a chance of being rejected. Therefore, contempt (self-esteem) is also associated.
In this example, both M and Microsoft successfully read the primary emotion (happiness) from the person’s facial expression.
The difference between M and Microsoft’s Azure is that to Azure, the face registered as completely happy, while M identified the presence of micro-expressions in addition to the primary emotion “happiness”.
M identified 15.4% “contempt” and 6.2% “surprise” as the secondary emotions during this instance of flirting. Indeed, both secondary emotions are related to flirting. The “contemptuous” and “surprising” emotions derived from one’s self-esteem and interest of finding an attractive one respectively. The emotional Artificial Intelligence Platform should be able to identify profound human emotions such as flirting in depth.
Your LIKE means a lot to us!
Follow Project M on:
Company website: http://www.ipmdinc.com
Facebook: Project M
*As of July 2019, the Project M team has devoted 64,000 hours to the AI platform, M. The sample input data we are using is the pure testing data that is completely new to M and Microsoft (assumed) and has never been used to train M, so this comparison is a fair trial between M and Microsoft. We appreciate Microsoft, the leader of the industry and emotional AI sector, for allowing the general public to test their testing site for identifying human emotions based on facial expressions.