Social Media Algorithm IDs Trump as Not Married
When scientists from Russia and Singapore tested an algorithm they created that that predicts marital status using data from three social networks, they found the program identified President Donald Trump as single. He is actually married to Melania Trump, his third wife.
Source: Janice Wood
According to the developers of the algorithm, this inconsistency came up because of Trump’s abnormal activity in the media: He and his associates use Twitter like a bachelor.
Mathematicians from ITMO University in Saint Petersburg, Russia, and the National University of Singapore discovered that profiling users through several social networks rather than just one makes it possible to learn specific details about individuals. In particular, the researchers focused on marital status.
Combining data from Twitter, Instagram, and Foursquare, they taught the algorithm to predict this parameter with 86 percent precision, 17 percent higher than using just one social network, researchers noted.
According to the researchers, the algorithm can examine any English-speaking account. To demonstrate how the program operates, Andrey Filchenkov, an associate professor of Computer Technology at ITMO University, collected and analyzed tweets of President Barack Obama and Trump.
Based on this data, the algorithm confirmed Obama’s marital status, but concluded that Trump is a bachelor.
This irregularity can be explained by the fact that Trump himself does not update his social media accounts, the researchers said.
“We all know about his wife Melania,” Filchenkov said. “But in this case, we are studying whether all Trump’s assistants are married or not. We are not guessing who Trump is, but who runs his social media.”
To train the algorithm to understand the data, the scientists turned the activity of users from New York, Singapore, and London into sets, or vectors, of parameters, such as average tweet size, the most frequent objects in a photo, check-in distribution, and so on. Then developers used these vectors in basic machine learning models.
Co-author Kseniya Buraya, a researcher at ITMO University, is doing an internship at National University of Singapore, where she studies approaches for describing human personality through social networks. She processes user data with this algorithm and then adapts the information to the Myers-Briggs Type Indicator (MBTI), a scale of psychological types.
The scale describes a person in terms of how he or she interacts with the world which, in turn, is easiest to learn from social media.
“Many scientific sources associate a person’s psychological type with his marital status,” Buraya said. “So we decided to check how precisely we can predict this parameter to use it for making human psychological portraits in the future.”
User profiling, according to the researchers, can have a wide range of applications. For example, recruiters can learn more about people who are applying for a job. Characterizing personality through activity in social media also could help discover illegal groups, as well as find people prone to depression or suicide and support them, the researchers said.
The study was presented at the AAAI Conference on Artificial Intelligence in San Francisco.