Dataset Information

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.

SUBMITTER: Badal VD

PROVIDER: S-EPMC8635064 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundReminiscence is the act of thinking or talking about personal experiences that occurred in the past. It is a central task of old age that is essential for healthy aging, and it serves multiple functions, such as decision-making and introspection, transmitting life lessons, and bonding with others. The study of social reminiscence behavior in everyday life can be used to generate data and detect reminiscence from general conversations.ObjectiveThe aims of this original paper are to (1) preprocess coded transcripts of conversations in German of older adults with natural language processing (NLP), and (2) implement and evaluate learning strategies using different NLP features and machine learning algorithms to detect reminiscence in a corpus of transcripts.MethodsThe methods in this study comprise (1) collecting and coding of transcripts of older adults' conversations in German, (2) preprocessing transcripts to generate NLP features (bag-of-words models, part-of-speech tags, pretrained German word embeddings), and (3) training machine learning models to detect reminiscence using random forests, support vector machines, and adaptive and extreme gradient boosting algorithms. The data set comprises 2214 transcripts, including 109 transcripts with reminiscence. Due to class imbalance in the data, we introduced three learning strategies: (1) class-weighted learning, (2) a meta-classifier consisting of a voting ensemble, and (3) data augmentation with the Synthetic Minority Oversampling Technique (SMOTE) algorithm. For each learning strategy, we performed cross-validation on a random sample of the training data set of transcripts. We computed the area under the curve (AUC), the average precision (AP), precision, recall, as well as F1 score and specificity measures on the test data, for all combinations of NLP features, algorithms, and learning strategies.ResultsClass-weighted support vector machines on bag-of-words features outperformed all other classifiers (AUC=0.91, AP=0.56, precision=0.5, recall=0.45, F1=0.48, specificity=0.98), followed by support vector machines on SMOTE-augmented data and word embeddings features (AUC=0.89, AP=0.54, precision=0.35, recall=0.59, F1=0.44, specificity=0.94). For the meta-classifier strategy, adaptive and extreme gradient boosting algorithms trained on word embeddings and bag-of-words outperformed all other classifiers and NLP features; however, the performance of the meta-classifier learning strategy was lower compared to other strategies, with highly imbalanced precision-recall trade-offs.ConclusionsThis study provides evidence of the applicability of NLP and machine learning pipelines for the automated detection of reminiscence in older adults' everyday conversations in German. The methods and findings of this study could be relevant for designing unobtrusive computer systems for the real-time detection of social reminiscence in the everyday life of older adults and classifying their functions. With further improvements, these systems could be deployed in health interventions aimed at improving older adults' well-being by promoting self-reflection and suggesting coping strategies to be used in the case of dysfunctional reminiscence cases, which can undermine physical and mental health.

Project description:BackgroundLoneliness and social isolation are growing public health concerns in our ageing society. Whilst these experiences occur across the life span, 50% of individuals aged over 60 are at risk of social isolation and one-third will experience some degree of loneliness later in life. The aim of this scoping review was to describe the range of interventions to reduce loneliness and social isolation among older adults that have been evaluated; in terms of intervention conceptualisation, categorisation, and components.MethodsThree electronic databases (CINAHL, Embase and Medline) were systematically searched for relevant published reviews of interventions for loneliness and social isolation. Inclusion criteria were: review of any type, published in English, a target population of older people and reported data on the categorisation of loneliness and/or social isolation interventions. Data extracted included: categories of interventions and the reasoning underpinning this categorisation. The methodology framework proposed by Arskey and O'Malley and further developed by Levac, et al. was used to guide the scoping review process.ResultsA total of 33 reviews met the inclusion criteria, evaluating a range of interventions targeted at older people residing in the community or institutionalised settings. Authors of reviews included in this paper often used the same terms to categorise different intervention components and many did not provide a clear definition of these terms. There were inconsistent meanings attributed to intervention characteristics. Overall, interventions were commonly categorised on the basis of: 1) group or one-to-one delivery mode, 2) the goal of the intervention, and 3) the intervention type. Several authors replicated the categorisation system used in previous reviews.ConclusionMany interventions have been developed to combat loneliness and social isolation among older people. The individuality of the experience of loneliness and isolation may cause difficulty in the delivery of standardised interventions. There is no one-size-fits-all approach to addressing loneliness or social isolation, and hence the need to tailor interventions to suit the needs of individuals, specific groups or the degree of loneliness experienced. Therefore, future research should be aimed at discerning what intervention works for whom, in what particular context and how.

Project description:BackgroundThere is a compelling need for an innovative and creative approach to promote social connectedness among older adults to optimize their well-being and quality of life. One possible solution may be through a digital intergenerational program.ObjectiveThis realist review aimed to identify existing digital intergenerational programs that were used to reduce loneliness or social isolation among older adults and analyze them in terms of strategy, context, mechanisms, and outcomes.MethodsWe performed a realist review with an extensive search of published and gray literature. For scholarly literature, we searched PubMed, Embase, CINAHL, PsycINFO (Ovid), and Social Sciences Citation Index databases for articles published between January 2000 to August 2020. A grey literature search was performed using the Google search engine, and the search was completed in May 2021. We included programs that evaluated digital intergenerational programs for older adults, which described outcomes of loneliness or social isolation. We included quantitative, mixed methods, and qualitative studies, as well as relevant theoretical papers, policy documents, and implementation documents. The studies were appraised based on their relevance and rigor. We synthesized the available evidence from the literature into Strategy-Context-Mechanism-Outcome (S-C-M-O) configurations to better understand what, when, and how programs work.ResultsA total of 31 documents reporting 27 digital intergenerational programs were reviewed. Our final results identified 4 S-C-M-O configurations. For S-C-M-O configuration 1, we found that for community-dwelling older adults, provision of access to and training in digital technology may increase older adults' self-efficacy in digital devices and therefore increase the use of digital communication with family. In S-C-M-O configuration 2, digital psychosocial support and educational interventions from nurses were found to be useful in reducing loneliness among community-dwelling older adults. In S-C-M-O configuration 3, a video call with a student or family was found to reduce loneliness among older adults residing in long-term residential care facilities. Finally, for S-C-M-O configuration 4, we found that behavioral activation provided through videoconferencing by a lay coach may be useful in reducing loneliness among older adults who are lonely. However, as almost half (11/27, 41%) of the included programs only reported quantitative results, this review focused on screening the discussion section of publications to identify author opinions or any qualitative information to elucidate the mechanisms of how programs work.ConclusionsThis review identified the key strategy, context, and mechanism influencing the success of programs that promote intergenerational interaction through digital means. This review revealed that different strategies should be adopted for different groups of older adults (eg, older adults who are lonely, older adults who reside in long-term residential care facilities, and community-dwelling older adults). The S-C-M-O configurations should be considered when designing and implementing digital intergenerational programs for older adults.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets