UCSD Team Uses Artificial Intelligence to Predict Loneliness in Older Adults

A study published in the American Journal of Geriatric Psychiatry detailed how researchers used artificial intelligence to analyze language patterns of older adults to determine degrees of loneliness, reports NBC San Diego . "We used natural language processing or NLP, an unbiased quantitative assessment of expressed emotion and sentiment, in concert with the usual loneliness measurement tools," said University of California, San Diego School of Medicine Professor Ellen Lee. The research focused on 80 independent senior living residents aged 66 to 94, average age 83. The study highlighted that lonely individuals took longer to respond in qualitative interviews, and more greatly expressed sadness to direct questions about loneliness. Moreover, women were more likely than men to admit feeling lonely during interviews, while men used more fearful and joyful words in their responses than women. The machine learning models predicted qualitative loneliness with 94 percent accuracy. Preliminary findings suggest that there may be "lonely speech" that could be used to identify loneliness in older adults, improving how clinicians and families evaluate and treat loneliness, especially during physical distancing and social isolation.