Author ORCID Identifier

https://orcid.org/0000-0002-7132-8244

Date of Award

2022

Document Type

Thesis (Undergraduate)

Department

Computer Science

First Advisor

Andrew T. Campbell

Abstract

As the critical phase of the COVID-19 pandemic seems to be winding down, it is important to analyze the adjustment to COVID-19 and return to normalcy of various populations. In this study we focus on the behavioral adjustments exhibited by a cohort of N=114 college seniors. To infer COVID-19 adjustment we compare the 2021 year (second year of COVID-19) to the 2020 year (first year of COVID-19) and 2019 (prepandemic baseline year). We begin with a broad analysis between the second and first covid year, finding that the second year of COVID-19 shows significant returns to pre-pandemic baselines on multiple sensing features. Further, we run statistical comparisons between the terms of Fall 2020 (lockdown fall), Fall 2019 (pre-covid fall) and Fall 2021 (postlockdown fall) and note statistically significant differences between Fall 2021 and Fall 2019 on four variables of interest. We find that activity variables surpass their pre-pandemic baseline, while smartphone usage variables still lag in their return. This suggests that disruptions to physical activity are easier to correct for, whereas smartphone and technology use display more permanent shifts once disrupted. We then use a multivariate forecasting method trained on Fall 2019 to forecast the entirety of Fall 2021, yielding an average Mean Absolure Relative Range Error of 12.15 indicating similarity between the terms. Finally, we perform a clustering analysis to understand whether there are any differences in how students react to the omicron and delta waves of COVID-19. One of our clusterings returns a cluster of students with a delayed return to baseline, while the other returns a few outlier students that exhibit dramatic shifts in behavior around the time the Omicron variant appears.

Download

Share

COinS