Living in a pandemic: changes in mobility routines, social activity and adherence to COVID-19 protective measures

Abstract

Non-Pharmaceutical Interventions (NPIs), aimed at reducing the diffusion of the COVID-19 pandemic, have dramatically influenced our everyday behaviour. In this work, we study how individuals adapted their daily movements and person-to-person contact patterns over time in response to the NPIs. We leverage longitudinal GPS mobility data of hundreds of thousands of anonymous individuals to empirically show and quantify the dramatic disruption in people's mobility habits and social behaviour. We find that local interventions did not just impact the number of visits to different venues but also how people experience them. Individuals spend less time in venues, preferring simpler and more predictable routines, also reducing person-to-person contacts. Moreover, we find that the individual patterns of visits are influenced by the strength of the NPIs policies, the local severity of the pandemic and a risk adaptation factor, which increases the people's mobility regardless of the stringency of interventions. Finally, despite the gradual recovery in visit patterns, we find that individuals continue to keep person-to-person contacts low. This apparent conflict hints that the evolution of policy adherence should be carefully addressed by policymakers, epidemiologists and mobility experts.

Figure 1

(A) From an individual’s original GPS trajectory, we detect a stop whenever the individual spends at least 5 minutes within a distance of 65 meters from a given trajectory point. (B) We detect stop locations through a combination of the Lachesis and DBSCAN algorithms. (C) If present, we associate each stop location to the nearest Point Of Interest (POI) within a distance of 65 m.

Figure 2

Changes in number and duration of visits to all POIs in the states of Arizona, Kentucky, New York and Oklahoma. (A) Percentage change over time in the number of visits with respect to the baseline period (3 January 2020–28 February 2020) for all types of venues. (B) Change in percentage of the duration of visits over time with respect to the baseline period of the median duration of visits to all POIs. For visualization purposes, the original curves are smoothed using a rolling average of seven days.

Figure 3

Changes in number and duration of visits to POIs in the state of New York. (A) Percentage change over time in the number of visits with respect to the baseline period (3 January 2020–28 February 2020) for venues in the Food and Shop & Service categories. (B) Change in percentage of the duration of visits over time with respect to the baseline period of the median duration of visits to Food and Shop & Service POIs. For visualization purposes, the original curves are smoothed using a rolling average of seven days. Vertical dashed lines indicate the date of restrictions and orders imposed by the state of New York government. (C) Percentage of time spent by people at Residential, Work, POIs, Other, and Moving (i.e. people in movement). (D) Percentage of time spent by people in venues under the eight first-level categories of POIs.

Figure 4

Changes in routine behaviour before and during the pandemic periods. (A, B) Network of the subsequent movements between POI categories for all users in the state of New York before and during the pandemic. The thickness of the links is proportional to the square root of the number of movements between the two POI categories. For visualization purposes we are showing only links for which the average number of daily movements is greater than $1/10000$. Pre-pandemic (C) and during-pandemic (D) distributions of these intensities excluding self-loops (e.g., Residential $\leftrightarrow$ Residential, Food $\leftrightarrow$ Food connections). Jaccard similarity matrix between individuals’ routines before the pandemic (E) and during the pandemic (F).

Figure 5

Co-location events. (A) Percentage change of co-location events from the baseline (until 29 February 2020) in New York state. We measure the change in co-location events for Residential areas (only one of the two individuals is in proximity of their residential area), POI (both individuals are at the same POI), Workplace (both individuals have the same work location) and Other co-location events. (B, C) We compare the difference between the expected and observed number and duration of co-location events. During the pandemic, individuals tend to have fewer and shorter co-locations than expected.