Tag: emoticons

Emotional glasses

Image by Km Nazrul Islam from Pixabay

It’s fun to add emoticons to messages, and they help ensure people understand our feelings. They are helping some people understand feelings face-to-face too, with a bit of help from an Artificial Intelligence.

Reading faces

We take it for granted that we can look at someone’s face and tell whether they are happy or sad, angry or surprised. Autistic children, however, often struggle to understand people’s expressions. When anxious we also all tend to avoid eye contact. Some autistic children do that all the time. They are then even less likely to see the clues in people’s faces, and so start to understand emotions. This can make it harder to make friends.

From robots to glasses

Many hi-tech ways have been tried to help autistic children learn about emotions. One, for example, involves letting them play with robot ‘friends’ as some find the cartoon-like expressions on a robot face more comfortable and easier to follow. A different approach is based on wearable technology. Researchers at Stanford University have created a program for autistic children that works out a person’s expression and displays an emoticon of it in a pair of smart glasses.

An AI reading faces for you

A camera in the glasses records what the wearer sees and the Artificial Intelligence (AI) program detects any faces. This kind of technology is also used in smartphones to detect faces in your photo collection. It uses ‘machine learning’: the program learns what a face is by being shown lots of images, some with and some without faces. The program uses all that data to work out the patterns in an image that mean there is a face. It then uses that pattern to spot new faces.

In a similar way it can be trained on faces with different expressions. A training set of faces are used that are labelled with the emotion in that image. This allows the program to spot what pattern in a face makes a happy face, what makes a sad face, and so on. Having recognised an expression, the glasses finally act as a screen and show an emoticon, such as a smiley, corresponding to that expression. Superimposing digital images on the real world like this is called augmented reality. It makes looking at faces like a game and means that the child can use the emoticon to understand what the person in front of them is feeling. It also means they can start to learn for themselves – almost like the AI! The AI is labelling the faces for them, just as people had done for it. With the glasses, autistic children can be sure what each face is actually saying rather than having to guess. Eventually they might then form their own rules and so do it on their own.

Making a difference

The Stanford system was trialled with autistic children in their own homes. They used the system for several months and their parents found it made a clear difference. By the end many of the children were engaging much more with their family including making a lot more eye contact.

Emoticons are making a real difference to their lives.

Paul Curzon, Queen Mary University of London

More on…

Related Magazine …

Subscribe to be notified whenever we publish a new post to the CS4FN blog.

Computers that read emotions

by Matthew Purver, Queen Mary University of London

Yellow balls with different expressions
Emoticons image by Gino Crescoli from Pixabay

One of the ways that computers could be more like humans – and maybe pass the Turing test – is by responding to emotion. But how could a computer learn to read human emotions out of words? Matthew Purver of Queen Mary University of London tells us how.

Have you ever thought about why you add emoticons to your text messages – symbols like 🙂 and :-@? Why do we do this with some messages but not with others? And why do we use different words, symbols and abbreviations in texts, Twitter messages, Facebook status updates and formal writing?

In face-to-face conversation, we get a lot of information from the way someone sounds, their facial expressions, and their gestures. In particular, this is the way we convey much of our emotional information – how happy or annoyed we’re feeling about what we’re saying. But when we’re sending a written message, these audio-visual cues are lost – so we have to think of other ways to convey the same information. The ways we choose to do this depend on the space we have available, and on what we think other people will understand. If we’re writing a book or an article, with lots of space and time available, we can use extra words to fully describe our point of view. But if we’re writing an SMS message when we’re short of time and the phone keypad takes time to use, or if we’re writing on Twitter and only have 140 characters of space, then we need to think of other conventions. Humans are very good at this – we can invent and understand new symbols, words or abbreviations quite easily. If you hadn’t seen the 😀 symbol before, you can probably guess what it means – especially if you know something about the person texting you, and what you’re talking about.

But computers are terrible at this. They’re generally bad at guessing new things, and they’re bad at understanding the way we naturally express ourselves. So if computers need to understand what people are writing to each other in short messages like on Twitter or Facebook, we have a problem. But this is something researchers would really like to do: for example, researchers in France, Germany and Ireland have all found that Twitter opinions can help predict election results, sometimes better than standard exit polls – and if we could accurately understand whether people are feeling happy or angry about a candidate when they tweet about them, we’d have a powerful tool for understanding popular opinion. Similarly we could automatically find out whether people liked a new product when it was launched; and some research even suggests you could even predict the stock market. But how do we teach computers to understand emotional content, and learn to adapt to the new ways we express it?

One answer might be in a class of techniques called semi-supervised learning. By taking some example messages in which the authors have made the emotional content very clear (using emoticons, or specific conventions like Twitter’s #fail or abbreviations like LOL), we can give ourselves a foundation to build on. A computer can learn the words and phrases that seem to be associated with these clear emotions, so it understands this limited set of messages. Then, by allowing it to find new data with the same words and phrases, it can learn new examples for itself. Eventually, it can learn new symbols or phrases if it sees them together with emotional patterns it already knows enough times to be confident, and then we’re on our way towards an emotionally aware computer. However, we’re still a fair way off getting it right all the time, every time.

Related Magazine …

EPSRC supports this blog through research grant EP/W033615/1.