M vs Microsoft Episode 29
Updated: Dec 8, 2022
Can Emotional AI Identify Subtle Negative Emotions?
This image depicts a little girl who was unfortunately physically and mentally abused. As we know child abuse happens when someone caring for a child hurts a child’s feelings or body. It can happen to any child in any family in any place. And often, hurt feelings (or emotional trauma) last much longer than a hurt body that can heal faster.
Now let’s see what M identifies:
Often this emotional trauma leads to mental disorders such as anxiety and depression, which can be translated into fear and sadness. M correctly identifies her emotional state as Fear at 55% and Sad at 33%.
How about Microsoft Azure?
Microsoft Azure fails to recognize the true emotional state of this girl because it identifies her emotional state as Neutral at 98% which means that the child in the image is not experiencing any emotions, for example, when we are spacing out at times or just gazing at something with no particular emotions, which is not right in this case as we have seen in the above M’s screening.
Because Microsoft uses computer vision, based on facial muscle movements to identify human emotions, and because the girl doesn’t exhibit much facial muscle movement, it incorrectly identifies her emotional state as Neutral.
Child Welfare Information Getaway
According to the childwelfare.gov, many cases of child abuse and neglect are not reported. Child can feel ashamed of the fact that they are abused and often times, they keep silent. We believe Project M can solve these particular problems.
The earlier abuse is identified and stopped, the earlier medical care, therapy, and counseling can help children and families heal.
Now that you know the context behind the situation and the two different emotional readings, it is up to you to decide what interpretation you think is most accurate. We, at IPMD, believe in the ability of emotional artificial intelligence platform to identify and understand obvious negative emotions has great potential to optimize humans’ emotional well-being.
Follow us on our social media and look out for our next episode!
Your LIKE means a lot to us! Follow Project M on:
*As of May 1, 2021, the Project M team has devoted 108,000 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.