Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing

Abstract

Introduction: Social isolation and loneliness (SI/L) are growing problems with serious health implications for older adults, especially in light of the COVID-19 pandemic. We examined transcripts from semi-structured interviews with 97 older adults (mean age 83 years) to identify linguistic features of SI/L.Methods: Natural Language Processing (NLP) methods were used to identify relevant interview segments (responses to specific questions), extract the type and number of social contacts and linguistic features such as sentiment, parts-of-speech, and syntactic complexity. We examined: (1) associations of NLP-derived assessments of social relationships and linguistic features with validated self-report assessments of social support and loneliness; and (2) important linguistic features for detecting individuals with higher level of SI/L by using machine learning (ML) models.Results: NLP-derived assessments of social relationships were associated with self-reported assessments of social support and loneliness, though these associations were stronger in women than in men. Usage of first-person plural pronouns was negatively associated with loneliness in women and positively associated with emotional support in men. ML analysis using leave-one-out methodology showed good performance (F1 = 0.73, AUC = 0.75, specificity = 0.76, and sensitivity = 0.69) of the binary classification models in detecting individuals with higher level of SI/L. Comparable performance were also observed when classifying social and emotional support measures. Using ML models, we identified several linguistic features (including use of first-person plural pronouns, sentiment, sentence complexity, and sentence similarity) that most strongly predicted scores on scales for loneliness and social support.Discussion: Linguistic data can provide unique insights into SI/L among older adults beyond scale-based assessments, though there are consistent gender differences. Future research studies that incorporate diverse linguistic features as well as other behavioral data-streams may be better able to capture the complexity of social functioning in older adults and identification of target subpopulations for future interventions. Given the novelty, use of NLP should include prospective consideration of bias, fairness, accountability, and related ethical and social implications.

Automatic Assessment of Loneliness in Older Adults Using Speech Analysis on Responses to Daily Life Questions

“…With increasing loneliness scores, the acoustic features showed decreased F2 and reduced the variance of ΔMFCCs, the prosodic features showed decreased pitch variation and increased pause duration, and the linguistic features showed a decrease in the number of positive words and an increase in the proportion of filler words ( Figure 4A and Supplementary Table 3 ). After controlling for age and sex as potential confounding factors ( 35 , 73 , 74 ), 15 of the 21 speech features remain correlated with loneliness scores ( Supplementary Table 3 ).…”

A Corpus-Based Study of the Matrix and Transgenderism

“…According to Badal et al (2021), individuals who are lonely may have higher usage of firstperson singular pronouns, which may reflect a lack of social contacts, close family members, or significant others, signaling a lack of closeness or commonality with other social contacts. In…”

The Promise of Artificial Intelligence in Supporting an Aging Population

“…Finally, natural language processing (NLP) refers to how computers can be used to understand and manipulate natural language, such as speech or text to perform to perform desired tasks (Chowdhury, 2003). For example, NLP might be used to examine speech patterns to model changes in cognitive functioning (Graham et al, (2020) or to detect social isolation and loneliness among older adults (Badal et al, 2021).…”

“…Other applications such as natural language processing (NLP) also hold potential for older adults. Badal and colleagues (Badal et al, 2021) demonstrate how natural language processing (NLP) can be used to quantify sentiment and features that indicate loneliness in transcribed speech text of older adults. The sample in their study included 80 older adults ranging in age from 66 to 94, who completed audio-taped interviews.…”