I'm alone but not lonely. U-shaped pattern of self-perceived loneliness during the COVID-19 pandemic in the UK and Greece

Abstract

Objectives: In the past months, many countries have adopted varying degrees of lockdown restrictions to control the spread of the COVID-19 virus. According to the existing literature, some consequences of lockdown restrictions on people's lives are beginning to emerge yet the evolution of such consequences in relation to the time spent in lockdown is understudied. To inform policies involving lockdown restrictions, this study adopted a data-driven Machine Learning approach to uncover the short-term time-related effects of lockdown on people's physical and mental health.

Study design: An online questionnaire was launched on 17 April 2020, distributed through convenience sampling and was self-completed by 2,276 people from 66 different countries.

Methods: Focusing on the UK sample (N = 325), 12 aggregated variables representing the participant's living environment, physical and mental health were used to train a RandomForest model to estimate the week of survey completion.

Results: Using an index of importance, Self-Perceived Loneliness was identified as the most influential variable for estimating the time spent in lockdown. A significant U-shaped curve emerged for loneliness levels, with lower scores reported by participants who took part in the study during the 6th lockdown week (p = 0.009). The same pattern was replicated in the Greek sample (N = 137) for week 4 (p = 0.012) and 6 (p = 0.009) of lockdown.

Conclusions: From the trained Machine Learning model and the subsequent statistical analysis, Self-Perceived Loneliness varied across time in lockdown in the UK and Greek populations, with lower symptoms reported during the 4th and 6th lockdown weeks. This supports the dissociation between social support and loneliness, and suggests that social support strategies could be effective even in times of social isolation.

Keywords: COVID-19; Global study; Lockdown; Loneliness; Machine learning; Mental health.

Fig. 1

Design of the machine learning approach adopted in the current study. The UK dataset was divided into a training (75% of data; in blue) and a testing (25% of data; in orange) set. To train the model, the training set was randomly split into five folds. Four folds were given as input for the RandomForest's training on estimating the week of survey completion. The last fold (in violet) was used as a validation set to evaluate the training. Performances were evaluated by computing the Mean Squared Error (MSE) on the training and validation. Also, a ranking of feature importance was collected alongside. The same five folds were used five times to train and validate the model (violet arrow). The whole procedure, from the randomized split of the initial train partition, was repeated ten times, each time with five folds that were randomly selected (green arrow). From this standardized training procedure, 50 metrics of performance on training and validation in terms of MSE, together with 50 rankings of variables importance, were obtained for each parameter set (P) in the Random Forest. The optimal parameter P was eventually selected based on the average performance on validation, and the model was then evaluated on the testing set. A Borda count was computed on the rankings of variables importances to identify the best estimator on predicting the week of survey completion. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)

Fig. 2

Average importance of the 12 health-related variables selected to train the RandomForest model on estimating the week of survey completion. Gini normalized importance values - an indicator of feature relevance - are obtained by computing a Borda count on the variables importance rankings on each iteration of a 10x5 cross-validations training scheme.

Fig. 3

Cross-sectional U-shaped distribution of Self-Perceived Loneliness scores for each week for participants from the UK (N = 325; left) and Greece (N = 137; right). The orange line within each bar represents the median score for each week. Median was chosen over the mean as it is less influenced by extreme values - namely, outliers (represented in the picture by the circles). Week 7 for Greece has only the orange line, with no box, because only one participant took part in the study in that period. Weeks 8 and 9 for Greece do not have bars because no participant took part in the study during that period of time. (*p < 0.017; **p < 0.01). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)