Self-Perceived Loneliness and Depression During the COVID-19 Pandemic: a Two-Wave Replication Study

This is the README file for the scripts of the preprint "Self-Perceived Loneliness and Depression During the COVID-19 Pandemic: a Two-Wave Replication Study" by Carollo et al. (2022) <br> Access the pre-print here: https://ucl.scienceopen.com/document/read?vid=0769d88b-e572-48eb-9a71-23ea1d32cecf <br> Abstract: Background: The global COVID-19 pandemic has forced countries to impose strict lockdown restrictions and mandatory stay-at-home orders with varying impacts on individual’s health. Combining a data-driven machine learning paradigm and a statistical approach, our previous paper documented a U-shaped pattern in levels of self-perceived loneliness in both the UK and Greek populations during the first lockdown (17 April to 17 July 2020). The current paper aimed to test the robustness of these results by focusing on data from the first and second lockdown waves in the UK. Methods: We tested a) the impact of the chosen model on the identification of the most time-sensitive variable in the period spent in lockdown. Two new machine learning models - namely, support vector regressor (SVR) and multiple linear regressor (MLR) were adopted to identify the most time-sensitive variable in the UK dataset from wave 1 (n = 435). In the second part of the study, we tested b) whether the pattern of self-perceived loneliness found in the first UK national lockdown was generalizable to the second wave of UK lockdown (17 October 2020 to 31 January 2021). To do so, data from wave 2 of the UK lockdown (n = 263) was used to conduct a graphical and statistical inspection of the week-by-week distribution of self-perceived loneliness scores. Results: In both SVR and MLR models, depressive symptoms resulted to be the most time-sensitive variable during the lockdown period. Statistical analysis of depressive symptoms by week of lockdown resulted in a U-shaped pattern between week 3 to 7 of wave 1 of the UK national lockdown. Furthermore, despite the sample size by week in wave 2 was too small for having a meaningful statistical insight, a qualitative and descriptive approach was adopted and a graphical U-shaped distribution between week 3 and 9 of lockdown was observed. Conclusions: Consistent with past studies, study findings suggest that self-perceived loneliness and depressive symptoms may be two of the most relevant symptoms to address when imposing lockdown restrictions. <br> In particular, the folder includes the scripts for the pre-processing, training, and post-processing phases of the research. <br> ==== PRE-PROCESSING WAVE 1 DATASET ==== - "01_preprocessingWave1.py": this file include the pre-processing of the variables of interest for wave 1 data; - "02_participantsexcludedWave1.py": this file include the script adopted to implement the exclusion criteria of the study for wave 1 data; - "03_countryselectionWave1.py": this file include the script to select the UK dataset for wave 1. <br> ==== PRE-PROCESSING WAVE 2 DATASET ==== - "04_preprocessingWave1.py": this file include the pre-processing of the variables of interest for wave 2 data; - "05_participantsexcludedWave1.py": this file include the script adopted to implement the exclusion criteria of the study for wave 2 data; - "06_countryselectionWave1.py": this file include the script to select the UK dataset for wave 2. <br> ==== TRAINING ==== - "07_MLR.py": this file includes the script to run the multiple regression model; - "08_SVM.py": this file includes the script to run the support vector regression model. <br> ==== POST-PROCESSING: STATISTICAL ANALYSIS ==== - "09_KruskalWallisTests.py": this file includes the script to run the multipair and the pairwise Kruskal-Wallis tests. <br>

本文件为Carollo等人（2022年）发表的预印本"新冠大流行期间的自我感知孤独与抑郁：两波重复研究"（Self-Perceived Loneliness and Depression During the COVID-19 Pandemic: a Two-Wave Replication Study）配套脚本的说明文档。
可通过以下链接获取该预印本：https://ucl.scienceopen.com/document/read?vid=0769d88b-e572-48eb-9a71-23ea1d32cecf

研究摘要：
研究背景：全球新冠疫情大流行迫使各国实施严格的封控措施与强制居家令，此类政策对个体健康的影响存在异质性。本团队此前的研究结合数据驱动的机器学习范式与统计学方法，发现2020年4月17日至7月17日首轮封控期间，英国与希腊人群的自我感知孤独感水平均呈现U型分布。本研究旨在聚焦英国首轮与第二轮封控队列数据，验证上述研究结果的稳健性。
研究方法：本研究开展两项验证：① 探究所选模型对封控期内最具时间敏感性变量识别的影响。本研究采用两种新型机器学习模型——支持向量回归器（support vector regressor, SVR）与多重线性回归器（multiple linear regressor, MLR），对英国首轮封控队列（n=435）的数据进行最具时间敏感性变量的识别。② 验证英国首轮全国封控中发现的自我感知孤独感分布模式是否可推广至英国第二轮封控队列（2020年10月17日至2021年1月31日）。为此，本研究使用英国第二轮封控队列数据（n=263），对自我感知孤独感得分的周度分布进行图形化与统计学检验。
研究结果：在SVR与MLR模型中，抑郁症状均为封控期内最具时间敏感性的变量。对英国首轮封控队列第3至7周的抑郁症状进行周度统计学分析后，发现其呈现U型分布。此外，尽管第二轮封控队列的周度样本量过小，无法获得具有统计学意义的分析结果，但本研究采用质性与描述性分析方法，仍观察到封控第3至9周的自我感知孤独感得分呈现图形化U型分布。
研究结论：与既往研究结果一致，本研究发现，在实施封控措施时，自我感知孤独感与抑郁症状是最需要关注的两类症状。

具体而言，本文件夹包含本研究预处理、训练与后处理阶段的所有脚本。

==== 首轮封控队列数据预处理 ====
- `01_preprocessingWave1.py`：该脚本用于首轮封控队列数据的目标变量预处理；
- `02_participantsexcludedWave1.py`：该脚本用于执行首轮封控队列数据的研究排除标准；
- `03_countryselectionWave1.py`：该脚本用于从首轮封控队列数据中筛选英国人群数据集。

==== 第二轮封控队列数据预处理 ====
- `04_preprocessingWave1.py`：该脚本用于第二轮封控队列数据的目标变量预处理；
- `05_participantsexcludedWave1.py`：该脚本用于执行第二轮封控队列数据的研究排除标准；
- `06_countryselectionWave1.py`：该脚本用于从第二轮封控队列数据中筛选英国人群数据集。

==== 模型训练 ====
- `07_MLR.py`：该脚本用于运行多重线性回归模型；
- `08_SVM.py`：该脚本用于运行支持向量回归模型。

==== 后处理：统计学分析 ====
- `09_KruskalWallisTests.py`：该脚本用于运行多组与组间克鲁斯卡尔-沃利斯检验（Kruskal-Wallis Test）。