We know that artificial intelligence (AI) is smart enough to do a few things our minds cannot, and with incredible accuracy. And now, it seems it also has the capacity to detect loneliness in humans, which is an otherwise challenging task.
A new study, led by researchers at the University of California San Diego School of Medicine, US, has shown how AI tools can predict levels of loneliness from a person’s speech with an accuracy rate of 94 percent.
The study focused on 80 participants aged 66 to 94, a population particularly vulnerable to loneliness. The subjects were asked 20 questions from the UCLA Loneliness Scale, which uses a four-point rating scale (量表) for questions such as “How often do you feel left out?” and “How often do you feel part of a group of friends?”
They were also interviewed in private conversations, which were recorded and transcribed (转录) by researchers. The transcripts (文字记录) were then examined using natural language processing (处理) tools, including IBM Watson Natural Language Understanding (WNLU) software, to quantify (量化) expressed emotions.
The interesting thing about this system is that it not only uses dictionary-based methods, such as searching for specific words that express fear, but also presents corresponding patterns by testing the words used in the response.
Varsha Badal, the first author of the study, noted that the WNLU software system uses deep learning to extract (提取) data from keywords, categories, emotions and grammar.
“Natural language processing and machine learning can systematically examine long interviews from multiple individuals and explore how subtle (微妙的) speech features such as emotions may indicate loneliness,” Badal said. “Similar emotion analyses by humans would be open to bias (偏见), lack consistency, and require extensive (大量的) training to standardize.”
The more lonely a person felt, the longer their responses to direct questions regarding loneliness. The system was capable of not just detecting the degree of loneliness in each subject, but also showing differences between the way men and women spoke about loneliness. The men were found to use more fearful and joyful words in their responses, while the women tended to acknowledge feeling lonely during interviews.
Co-author Dilip Jeste said that the IBM-UC San Diego Center is now exploring natural language patterns of loneliness and wisdom, which are inversely (成反比地) linked in older adults. “Speech data can be combined with our other assessments (评估) of cognition (认知), mobility (运动), sleep, physical activity and mental health to improve understanding of aging and to help contribute to successful aging,” he said.
12. What can we know about the study?
A.It involved 80 middle-aged participants. |
B.It could reach as high as 90 percent in accuracy. |
C.It relied on AI tools from the beginning. |
D.Its original data was partly from private interviews. |
13. How did the WNLU software system contribute to the loneliness study?
A.By detecting speech patterns that show emotion. |
B.By removing bias from the transcribing process. |
C.By locating specific words in long conversations. |
D.By standardizing the training of emotion analyses. |
14. Which of the following is among the findings?
A.The lonelier the person is, the quicker they respond. |
B.The way we talk about loneliness varies with age. |
C.Lonelier people had longer responses about loneliness. |
D.Women tend to be more optimistic about loneliness. |
15. What does Dilip Jeste imply in the last paragraph?
A.The study is helpful for studying aging. |
B.AI tools can be applied to studying the secret of aging. |
C.Speech data is important for assessing cognition. |
D.The system’s accuracy needs to be improved. |