Highlights
- •What is the primary question addressed by this study? This paper explores the use of natural language processing techniques and machine learning models to predict loneliness in older community-dwelling adults.
- •What is the main finding of this study? There are structural differences in how older men and women talk about loneliness that can be detected using natural language processing techniques. Text features can be used to predict loneliness with reasonable validity.
- •What is the meaning of the finding? NLP and machine learning approaches provide a novel way to analyze text data to identify loneliness, while accounting for key sociodemographic factors like sex and age.
Abstract
Objective
The growing pandemic of loneliness has great relevance to aging populations, though
assessments are limited by self-report approaches. This paper explores the use of
artificial intelligence (AI) technology to evaluate interviews on loneliness, notably,
employing natural language processing (NLP) to quantify sentiment and features that
indicate loneliness in transcribed speech text of older adults.
Design
Participants completed semi-structured qualitative interviews regarding the experience
of loneliness and a quantitative self-report scale (University of California Los Angeles
or UCLA Loneliness scale) to assess loneliness. Lonely and non-lonely participants
(based on qualitative and quantitative assessments) were compared.
Setting
Independent living sector of a senior housing community in San Diego County.
Participants
Eighty English-speaking older adults with age range 66–94 (mean 83 years).
Measurements
Interviews were audiotaped and manually transcribed. Transcripts were examined using
NLP approaches to quantify sentiment and expressed emotions.
Results
Lonely individuals (by qualitative assessments) had longer responses with greater
expression of sadness to direct questions about loneliness. Women were more likely
to endorse feeling lonely during the qualitative interview. Men used more fearful
and joyful words in their responses. Using linguistic features, machine learning models
could predict qualitative loneliness with 94% precision (sensitivity = 0.90, specificity = 1.00)
and quantitative loneliness with 76% precision (sensitivity = 0.57, specificity = 0.89).
Conclusions
AI (e.g., NLP and machine learning approaches) can provide unique insights into how
linguistic features of transcribed speech data may reflect loneliness. Eventually
linguistic features could be used to assess loneliness of individuals, despite limitations
of commercially developed natural language understanding programs.
Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to The American Journal of Geriatric PsychiatryAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
REFERENCES
Lubben J, Gironda M, Sabbath E, et al. Social isolation presents a grand challenge for social work (Grand Challenges for Social Work Initiative Working Paper No. 7), 2015, Cleveland, OH: American Academy of Social Work and Social Welfare.
- Are U.S. older adults getting lonelier? Age, period, and cohort differences.Psychol Aging. 2019; 34: 1144-1157
- Predictors of loneliness among older women and men in Sweden: a national longitudinal study.Aging Ment Health. 2015; 19: 409-417
- Changing American Households.United States Census Bureau, Washington, D.C.2011
- Social Isolation and New Technology.Pew Internet & American Life Project, 2009
- Feelings of loneliness, but not social isolation, predict dementia onset: results from the Amsterdam Study of the Elderly (AMSTEL).J Neurol Neurosurg Psychiatry. 2014; 85: 135-142
- Loneliness and risk of Alzheimer disease.Arch Gen Psychiatry. 2007; 64: 234-240
- Loneliness and cognitive function in the older adult: a systematic review.Int Psychogeriatr. 2015; 27: 541-553
- Making the economic case for investing in actions to prevent and/or tackle loneliness: a systematic review.A Briefing paper. Personal Social Services Research Unit (PSSRU). London School of Economics and Political Science, London2017
- High prevalence and adverse health effects of loneliness in community-dwelling adults across the lifespan: role of wisdom as a protective factor.Int Psychogeriatr. 2019; 31: 1447-1462
- The trajectory of loneliness in response to COVID-19.Am Psychol. 2020; https://doi.org/10.1037/amp0000690
- Illuminating the psychological experience of elderly loneliness from a societal perspective: a qualitative study of alienation between older people and society.Int J Environ Res Public Health. 2017; 14: 824-842
- Being acknowledged by others and bracketing negative thoughts and feelings: frail older people's narrations of how existential loneliness is eased.Int J Older People Nurs. 2019; 14: e12213
- Loneliness, loss, and social support among cognitively intact older people with cancer, living in nursing homes–a mixed-methods study.Clin Interv Aging. 2015; 10: 1529-1536
- “It's the worst bloody feeling in the world”: experiences of loneliness and social isolation among older people living in care homes.J Aging Stud. 2019; 49: 74-84
- Qualitative study of loneliness in a senior housing community: the importance of wisdom and other coping strategies.Aging Ment Health. 2020; : 1-8https://doi.org/10.1080/13607863.2019.1699022
- Loneliness matters: a theoretical and empirical review of consequences and mechanisms.Ann Behav Med. 2010; 40: 218-227
- Gender differences in self-concept and psychological well-being in old age: a meta-analysis.J Gerontol Series B Psychol Sci Soc Sci. 2001; 56: P195-P213
- Foundations of Statistical Natural Language Processing. 1999;
- Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit.O'Reilly Media, Inc., 2009
- Predicting early psychiatric readmission with natural language processing of narrative discharge summaries.Transl Psychiatry. 2016; 6 (e921-e921)
- Novel use of natural language processing (NLP) to predict suicidal ideation and psychiatric symptoms in a text-based mental health intervention in Madrid.Comput Math Methods Med. 2016; 2016https://doi.org/10.1155/2016/8708434
- Identifying suicide ideation and suicidal attempts in a psychiatric clinical research database using natural language processing.Sci Rep. 2018; 8: 1-10
- Mental health-related conversations on social media and crisis episodes: a time-series regression analysis.Sci Rep. 2020; 10: 1342
- Predicting mental conditions based on “history of present illness” in psychiatric notes with deep neural networks.J Biomed Inform. 2017; 75: S138-S148
- Using electronic medical records to enable large-scale studies in psychiatry: treatment resistant depression as a model.Psychol Med. 2012; 42: 41-50
- Study of independent living residents of a continuing care senior housing community: sociodemographic and clinical associations of cognitive, physical, and mental health.Am J Geriatr Psychiatry. 2019; 27: 895-907
- The brief symptom inventory: an introductory report.Psychol Med. 1983; 13: 595-605
- The PHQ-9: validity of a briefdepression severity measure.J Gen Intern Med. 2001; 16: 606-613
- UCLA loneliness scale (Version 3): reliability, validity, and factor structure.J Pers Assess. 1996; 66: 20-40
- Identifying behavioral phenotypes of loneliness and social isolation with passive sensing: statistical analysis, data mining and machine learning of smartphone and fitbit data.JMIR Mhealth Uhealth. 2019; 7: e13209
- Qualitative Research and Evaluation Methods.3d ed. Sage, Thousand Oaks, CA2002
IBM WNLU: Available at:https://www.ibm.com/cloud/watson-natural-language-understanding?lnk=STW_US_STESCH&lnk2=trial_WatNatLangUnd&pexp=def&psrc=none&mhsrc=ibmsearch_a&mhq=NLU. Accessed February 24, 2020
- The measurement of observer agreement for categorical data.Biometrics. 1977; 33: 159-174
Joachims T: A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization, Pittsburgh, PA, School of Computer Science, Carnegie Mellon University, 1996
- An information-theoretic perspective of TF-IDF measures.Inf Process Manage. 2003; 39: 45-65
- Mining of Massive Datasets.Cambridge University Press, 2011
IBM Cloud API Docs, Natural Language Understanding, Available at: https://cloud.ibm.com/apidocs/natural-language-understanding/natural-language-understanding. Accessed March 4, 2020
- Emotions and life: perspectives from psychology, biology, and evolution.American Psychological Association, Washington, DC,. 2003;
IBM Watson: Sentiment and context analysis, Available at:https://www.pubnub.com/docs/blocks-catalog/group-sentiment-analysis. Accessed December 19, 2019
Ernst N: Cliff's delta, python. Available at: https://github.com/neilernst/cliffsDelta, Accessed August 25, 2020
- Orange: data mining toolbox in Python.J Mach Learn Res. 2013; 14: 2349-2353
- Popular ensemble methods: an empirical study.J Artif Intell Res. 1999; 11: 169-198
- Ensemble based systems in decision making.IEEE Circuits Syst Mag. 2006; 6: 21-45
- A Critical Review of Feature Selection Methods, in Feature Selection for High-Dimensional Data.Springer International Publishing, Cham2015: 29-60
- A review of feature selection methods in medical applications.Comput Biol Med. 2019; 112103375
- A review of feature selection techniques in bioinformatics.Bioinformatics. 2007; 23: 2507-2517
- Ensemble-based classifiers.Artif Intell Rev. 2010; 33: 1-39
Sollich P, Krogh A: Learning with ensembles: how overfitting can be useful, 1996
- Accuracy and diversity in ensembles of text categorisers.CLEI Electron J. 2005; 9: 1-12
- Who are lonely? Loneliness in different age groups (18-81 years old), using two measures of loneliness.Int J Aging Human Dev. 2014; 78: 229-257
- The De Jong Gierveld short scales for emotional and social loneliness: tested on data from 7 countries in the UN generations and gender surveys.Eur J Ageing. 2010; 7: 121-130
- Gender and marital-history differences in emotional and social loneliness among Dutch older adults.Can J Aging Revue Canadienne Vieillissement. 2004; 23: 141-155
- Loneliness, fear, and quality of life among elderly in Sweden: a gender perspective.Aging Clin Exp Res. 2005; 17: 494-501
- Augmenting qualitative text analysis with natural language processing: methodological study.J Med Internet Res. 2018; 20 (e231-e231)
- Natural Language Processing (NLP) in qualitative public health research: a proof of concept study.Int J Qual Methods. 2019; 18160940691988702
- Using natural language processing technology for qualitative data analysis.Int J Soc Res Methodol. 2012; 15: 523-543
Article info
Publication history
Published online: September 11, 2020
Accepted:
September 4,
2020
Received in revised form:
September 2,
2020
Received:
April 22,
2020
Identification
Copyright
Published by Elsevier Inc. on behalf of American Association for Geriatric Psychiatry.
