.png){kind=logo}
Can AI understand emotions related to competitiveness and failure?
What is happening here?
The man in the picture, Matt Stonie, is a professional, competitive eater who decides to take on the “GIANT Poutine Challenge”. Poutine is a Canadian dish, made of french fries, gravy and cheese curds - as you can imagine, it’s a hefty dish. In preparation for the upcoming World Poutine Eating Championship in Canada, Stonie is doing a mock run with a filmed timed at-home challenge of finishing a large, 13-pound bowl of poutine. For reference, that’s about 2x as heavy as a standard brick!
During the mock run, Stonie is initially consistent with his eating pace. However, as he becomes more full of food, he slows down, struggling to complete the dish in the end. Although he pushes himself to eat more, he is disgusted, nauseous and in pain. Stonie is unable to complete the challenge. His failure to complete the challenge is obviously disappointing and discouraging, given his skill and competitive nature.
Take a moment to think: what kinds of emotions could Stonie be feeling?
Since the image is captured while Stonie is in the middle of his mock run, the greatest emotion Stonie likely feels is disgust. As poutine is extremely salty and unhealthy, it is exceptionally difficult to force oneself to eat it in such large quantities. It is quite likely to cause unpleasant emotions such as disgust if one tries to do so.
Following disgust, Stonie may feel contempt and sadness because he found it difficult to finish his food. Though the image is captured in the middle of the mock run, Stonie is likely already aware that he is failing in his attempt. Because he is highly regarded in the competitive eating field, being unable to finish his food is damaging to his pride as well as his reputation. Lastly, Stonie possibly feels anger at himself because he is unable to maintain his high standards in eating.
Now Let’s see how M and Microsoft interpret the emotions that Stonie feels in the heat of the moment.
M vs Microsoft Analysis
M is detecting a high amount of disgust at 41%, which makes sense, considering Stonie is forcing himself to eat something, and this experience is highly unpleasant. Disgust is followed by contempt and sadness, both at 15%. The sadness and contempt can be explained by his unsatisfactory performance in completing the mock challenges, thus forsaking his pride and reputation.
However, in comparison, Microsoft detects neutral as the main emotion, at 79%, and anger at 13.5%. While we discussed anger being a possible emotion that Stonie is experiencing, neutral is not at all applicable to this scenario. We know from the context of the image that Stonie is in pain, and emotionally and physically challenging himself. This calls for much more varied and intense emotions, which is what M captures, but Microsoft does not.
Now that you know the context behind the situation, and the two different emotion readings, it is up to you to decide what interpretation you think is most accurate.
We at Project M believe the ability of emotional artificial intelligence platforms to identify and understand negative emotions has great potential to optimize humans’ emotional well being.
Follow us on our social media and stay tuned for our next episode!
Your LIKE means a lot to us! Follow Project M on:
Company website: http://www.ipmdinc.com
Medium: Project M
Facebook: Project M
Blogger: Project M
Instagram: mprojectai
Twitter: @mprojectai
*As of February 1, 2020, the Project M team has devoted 78,000 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.
Comments