Fig 1.
Example of format of structured and unstructured data.
Table 1.
Quantity of free text per person.
Table 2.
Characteristics of individuals in the training and test set.
Fig 2.
Overall training and evaluation process.
Table 3.
Classification outcomes across assessments and case notes.
Table 4.
Accuracy and F1 score of classification models.
Fig 3.
Confusion matrix (RoBERTa).
Fig 4.
Proportion of lonely/isolated by demographic characteristics: Administrative and survey data.
Table 5.
Factors in structured data associated with loneliness and social isolation: Administrative data and ELSA.
Table 6.
Comparison of demographic and ADL needs between ELSA waves 6–9 and administrative data.
Table 7.
Logistic regression: Association of loneliness extracted from free text with services received for loneliness.
Fig 5.
Examples of polysemy in adult social care case notes.