An AI companion for lonely seniors

Computing scientists at the University of Alberta are taking the first steps toward chatbots that can express and respond to emotion during a conversation—including artificially intelligent companions that could help relieve loneliness for seniors.

Photo
University of Alberta computing scientist Osmar Zaïane with the chatbot he and his team are developing that can express and respond to emotions
Source: Melanie Marvin

“Chatbots like Siri or Alexa are primarily used to look up information or do a task for you—answering questions in the shortest time possible,” said computing scientist Osmar Zaïane, co-author of the study and scientific director of the Alberta Machine Intelligence Institute (AMII). “We envision a device that’s emotionally intelligent, where an elderly person can say “I’m tired’ or “It’s beautiful outside,” or tell a story about their day—and receive a response that carries on the conversation and keeps them engaged.”

The team’s model was able to express responses that matched requested emotions in most cases—though Zaïane noted some emotions, like surprise and love, were easier to express than others, and this is just one of several steps in turning the vision of a digital companion into a reality. “In this study, we coached the program by telling it which emotion to express in its response. Our next study will focus on having the program independently decide on what emotion to express, depending on the persona it’s talking to,” said Zaïane.

Health experts agree loneliness poses a concern for health and quality of life among seniors, whose numbers are growing in Canada. “Loneliness leads to boredom and depression, which causes an overall deterioration in health,” explained Zaïane. “Studies show that companionship—a cat, a dog, other people—helps tremendously. The advantage for caregivers of a digital companion like this is it can also collect information on the emotional state of the person, noting if they are frequently feeling sad, for example.”

But developing AI capable of understanding when humans are expressing emotion and responding in an appropriate way is no small challenge, Zaïane noted. “When an elderly person tells you something that’s sad, it’s important to respond with empathy,” said Zaïane. “That requires that the device first understand the emotion that is expressed. We can do that by converting the speech to text and looking at the words that are used. In this study, we looked at the next step: having the program express emotions—like surprise, sadness, happiness—in its response.”

Subscribe to our newsletter

Related articles

AI detects rare diseases

AI detects rare diseases

With artificial intelligence to a diagnosis of rare hereditary diseases: The neural network combines data from portrait images with gene and patient data.

Are humans too slow for digitalisation?

Are humans too slow for digitalisation?

Today, drones are happily regarded as the pinnacle of digitalisation in healthcare. However, for Dr Dominik Pförringer, “Drones are not even in the top 100 of my wish list for digital solutions."

Covid-19: chatbots could be used to deliver psychotherapy

Covid-19: chatbots could be used to deliver psychotherapy

Researchers show chatbots could play a key role in helping people with issues around their health and wellbeing.

Digital twin enables protective ventilation

Digital twin enables protective ventilation

A computational lung model can be used to reduce damage caused by mechanical ventilation – and could increase survival rates for patients significantly.

COVID 19: AI to predict patients' risk of needing ventilators

COVID 19: AI to predict patients' risk of needing ventilators

Experts have begun using artificial intelligence to create computer models that calculate the risk of a corona patient’s needing intensive care or a ventilator.

Nexkin: multiparametric monitoring shirt launched

Nexkin: multiparametric monitoring shirt launched

Chronolife announced the launch of Nexkin, a washable smart T-shirt that monitors six key physiological parameters to enable prevention, risk reduction, and remote monitoring.

AI predicts success of digital health interventions

AI predicts success of digital health interventions

A new statistical technique from the field of machine learning is now making it possible to predict the success of smartphone-based interventions more accurately.

Mental health game changer

Mental health game changer

Using a simple computer game and AI techniques, researchers were able to identify behavioural patterns in subjects with depression and bipolar disorder.

Digital phenotyping helps to treat mental illness

Digital phenotyping helps to treat mental illness

Research shows that digital phenotyping can provide valuable information to mental health professionals about mental illness symptom severity and relapse.

Popular articles