Advertisement

Alberta scientists use machine learning and Twitter to better understand our health

Click to play video: 'Women are abused every 30 seconds on Twitter: Amnesty International'
Women are abused every 30 seconds on Twitter: Amnesty International
WATCH ABOVE: Amnesty International and Element AI, a global artificial intelligence software product company, surveyed millions of “problematic” tweets and found that women are abused every 30 seconds on Twitter – Dec 19, 2018

Many people share their well-being on social media, and University of Alberta scientists are using machine learning and Twitter to better understand your health.

Machine learning is an application of artificial intelligence (AI) that provides computers the ability to automatically learn and improve from experience without being explicitly programmed.

Computing scientists at the university said a machine learning tool called Grebe used data from Twitter to improve their understanding of the health and wellness of residents in Alberta and the rest of Canada.

READ MORE: The $100K entry-level job you can get here in Canada

“We use machine learning to determine where the location tweets refer to, the dimension of health they are related to, and the emotions expressed in each tweet,” computing science professor Osmar Zaiane said.

Story continues below advertisement

“If we can do this properly, we can get a better understanding of what it’s actually like to live in a particular place, in terms of health and wellness.”

READ MORE: University of Alberta students get in touch with well-being, mental health through WellTrack app

Receive the latest medical news and health information delivered to you every Sunday.

Get weekly health news

Receive the latest medical news and health information delivered to you every Sunday.
By providing your email address, you have read and agree to Global News' Terms and Conditions and Privacy Policy.

University of Alberta computing scientists said Grebe harnesses the power of machine learning to assist in the work of health monitoring organizations such as the Public Health Agency of Canada and the Centers for Disease Control and Prevention in the United States.

“Public health experts are interested in knowing what’s happening in a particular city or province,” Zaiane said.

“While surveys are useful forms of gathering information, self-reports can also be unreliable or inaccurate. This type of tool allows public health experts to study people’s behaviour, in addition to their self-reports.”

READ MORE: Website uses artificial intelligence to generate realistic human faces from scratch

The scientists said they used machine learning to identify physical, emotional, occupational, social spiritual and intellectual health, as well as the emotions expressed in each tweet and the relevant location.

The project began in Edmonton, before expanding to the rest of Alberta and then the remaining provinces.

“Our goal wasn’t to find the trends themselves. Rather, our goal was to build a tool that will let public health professionals and sociologists analyze these trends,” Zaiane said.

Story continues below advertisement

“This tool allows experts to go through another medium — in this case Twitter — to verify trends that they’ve found elsewhere, such as through surveys, as well as verifying other research.”

READ MORE: Alberta announces $100M, 5-year investment in artificial intelligence

In February, the Alberta government announced it plans to spend $100 million over five years to attract investment from artificial intelligence-focused tech companies.

The province said the money would go to Alberta Innovates, the province’s research development agency, and the non-profit Alberta Machine Intelligence Institute.

WATCH BELOW: Smart ‘chat bot’ devices are learning emotional intelligence in order to converse with humans

Click to play video: 'Smart ‘chat bot’ devices learn emotional intelligence in order to converse with humans'
Smart ‘chat bot’ devices learn emotional intelligence in order to converse with humans

Sponsored content

AdChoices