THE LANGUAGE OF LONELINESS: ANALYZING UNSTRUCTURED SPEECH TO DETECT LONELINESS AND SOCIAL ISOLATION
2024

Detecting Loneliness and Social Isolation through Speech Analysis

publication

Author Information

Author(s): Lee Ellen, Wang Ning, Badal varsha, Goel Sanchit, Subbalakshmi Koduvayur

Primary Institution: University of California San Diego

Hypothesis

Can unstructured speech data be used to detect loneliness and social isolation in older adults?

Conclusion

Analyzing speech data can help identify loneliness and social isolation, which are linked to negative health outcomes in older adults.

Supporting Evidence

  • Loneliness and social isolation can lead to increased mortality in older adults.
  • Current assessments of loneliness are lengthy and do not capture individual experiences.
  • Speech analysis can provide insights into social disconnection.

Takeaway

This study looks at how the way older people talk can show if they feel lonely or isolated, which can help doctors help them better.

Methodology

The study used Natural Language Processing and openSMILE to analyze speech data and identify features related to social disconnection.

Participant Demographics

Older adults living independently in senior housing communities in San Diego.

Digital Object Identifier (DOI)

10.1093/geroni/igae098.1881

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication