This was the year most every large company took notice of the rise of artificial intelligence. But while it encapsulates many categories – machine learning, deep learning, computer vision, natural language processing, speech recognition and others – there is still one category that hasn’t been recognized, beyond academia, and that’s emotion recognition; or affective computing.
Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. At Netek we frame affective computing as emotional artificial intelligence, or emotion AI.
The most fundamental application of emotional artificial intelligence (affective computing) will be to inform next-generation human interfaces that are able to recognize, and respond to, the emotional states of their users. Users who are becoming frustrated or annoyed with using a product would “send out signals” to the computer, at which point the application might respond in a variety of ways — ideally in ways that the user would see as “intuitive”.
What are some practical applications of emotion AI?
Below are 10 incredibly useful things emotional artificial intelligence can do:
1. Help marketers better determine their marketing mix
Marketing is a domain where emotion recognition is key. Companies would then be able to use affective computing to infer whether their products will or will not be well received by the respective market.
Our software, Vibetek, does exactly this.
2. Help recruiters make better hiring decisions
Recruiting is heavily biased. Can emotion recognition help eliminate some of that bias? Yes. Hire Vue is a company that uses emotion recognition during video interviews; they call it video intelligence.
3. Help robots interact with humans
While we’re getting used to”interacting” with Alexa, Cortana, Siri and Google; they don’t have the ability to recognize our emotions and craft an answer that addresses those emotions. Their answers are boilerplate responses which they’ve been trained to listen and respond to. But this will change as more cameras and sensors surround us, virtual assistants and robots will learn to detect emotions.
4. Help teachers enhance learning for their students
For example, a computer piano tutor might change its pace and presentation based upon naturally expressed signals that the user is interested, bored, confused, or frustrated. You can extend this to the classroom where a similar computer tutor can adapt to your mood and provide you with the right content to get you engaged.
5. Help banks determine who’s worthy of receiving credit
Though there are credit scores, there are many ways people game the system. Should everyone get credit? No. The right people should. Using emotion recognition banks could determine who’s really committed to making their payments on time.
6. Help users navigate to the “most exciting” scenes in a movie when using streaming providers like Netflix
Yes, you read that right. A video retrieval system might help identify not just scenes having a particular actor or setting, but scenes having a particular emotional content: fast-forward to the “most exciting” scenes.
7. Help your wearable moderate your stress levels
Your wearable computer could pay attention to things that increase your stress, so that it might help point them out and provide assistance to boost your immune system when needed.
8. Help your car provide additional safety measures when you’re driving
For example, a car can monitor the emotion of all occupants and engage in additional safety measures, such as alerting other vehicles if it detects the driver to be angry.
9. Help your music player select tracks based on your mood
Yes, this already exists within Spotify and other music streaming services. But it’s based on your “selection”; not the computer detecting your emotional state.
10. Help you communicate more effectively with your family or co-workers
Ever sent an email when mad? We all have and the results are probably mixed. Emotion recognition, via both text and video, could hold you off before clicking send on that email.
There are endless applications for emotion AI in all aspects of life; we’re just scratching the surface with these. What other useful things can emotional artificial intelligence do?
Originally published at Vibetek blog.
Also published on Medium.