Scientists Study and Predict Loneliness Through Artificial Intelligence

In Education

Loneliness is something that everyone goes through every once in a while, especially when in isolation. It is an emotion that might appear innocent, but it can get dangerous enough to push people to vices such as opioid use, and some people have even committed suicide due to loneliness.

Loneliness has been attributed to other issues, such as declining health and declining productivity. Scientists have taken up an interest in the topic of loneliness, which led to the launch of a study through which they used artificial intelligence to better understand the topic. The researchers from the University of California tapped into AI, which they used to evaluate natural language patterns. The approach allowed them to better understand the levels of loneliness, especially in adults.

“Most studies use either a direct question of ‘ how often do you feel lonely,’ which can lead to biased responses due to stigma associated with loneliness or the UCLA Loneliness Scale which does not explicitly use the word ‘lonely,'” stated Dr. Ellen Lee, an assistant psychiatry professor at the University of California school of medicine.

What type of data did the AI unlock as far as loneliness is concerned?

The AI-based study on loneliness evaluated 80 subjects between 66 and 94 years old. The scientists used NPL-understanding software created by IBM to examine the structured interviews involving the study subjects. The study’s role was to pick up on subtle speech features that point towards loneliness.

The AI findings indicate that women are more likely to admit that they are lonely compared to men. The AI also observed that individuals going through a loneliness phase were more likely to provide longer responses. The lonely individuals were also more likely to express their sadness when asked direct questions about loneliness. The study also revealed that men were more likely to use joyful or fearful words when responding to the questions than their female counterparts.

The authors involved in the study concluded that the AI-powered study results highlight ‘lonely speech’ can be an important thing to consider when determining the level of loneliness, especially in older adults. Physicians can use such data to determine the best type of treatment for the loneliness.

Mobile Sliding Menu