Acquired Electronics360

Medical Devices and Healthcare IT

Social Media Algorithm Identifies President Trump as “Not Married”

03 March 2017

Scientists from ITMO University in Saint Petersburg, Russia, and the National University of Singapore have created an algorithm that predicts the martial status of individuals based on three social media networks.

The scientists found that by profiling users through several social networks rather than just one, it is possible to learn specific details about individuals. Combining data from Twitter, Instagram and Foursquare, researchers taught the algorithm to predict marital status with 86 percent precision, 17 percent higher than just using one social network.

However, when it came to U.S. President Donald Trump, who is actually married, it listed him as being single. The inconsistency with the 45th U.S. President resulted from Trump’s abnormal activity in the media—the businessman and his assistants use Twitter like a bachelor would, researchers say. They also analyzed 44th U.S. President Barak Obama and correctly confirmed his marital status.

Researchers say the irregularity can be explained by the fact that Trump himself does not update his social media accounts. It is not guessing who Trump is, but who runs his social media, including any assistants that may be working on it.

Training of the algorithm involved taking input from users from New York, Singapore and London on the parameters such as an average tweet size, the most frequent objects in a photo, check-in distribution and so on. Researchers then used these vectors in basic machine learning models.

The user data inside the algorithm is then adapted to the Myers-Briggs Type Indicator (MBTI), a scale of psychological types. The scale determines how a person interacts with the world through social media.

“Many scientific sources associate a person's psychological type with his marital status,” says Kseniya Buraya, researcher at ITMO University's International Laboratory. “So, we decided to check how precisely we can predict this parameter to use it for making human psychological portraits in the future.”

This type of profiling could be used by recruiters to learn more about the people who apply for a job or help discover illegal groups that are using social media or find people prone to depression or suicide in order to give them support, researchers say.

To contact the author of this article, email Peter.Brown@ieeeglobalspec.com


Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the Engineering360
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement

CALENDAR OF EVENTS

Date Event Location
12-14 Sep 2017 Novi, MI
12-14 Sep 2017 Santa Clara, California
12-14 Sep 2017 Novi, MI
30 Nov-01 Dec 2017 Helsinki, Finland
23-27 Apr 2018 Oklahoma City, Oklahoma
Find Free Electronics Datasheets
Advertisement