Using Social Media Data to Evaluate Urban Parks Use during the COVID-19 Pandemic

Abstract

In the context of increasing urbanization and associated economic, social and environmental challenges, cities have increasingly acknowledged the importance of urban parks in delivering social, economic and environmental benefits to the population. The importance has been demonstrated also during the COVID-19 pandemic that generated lockdowns and reduced the capacity of urban inhabitants in accessing such benefits. The present study aims to determine how the presence in urban parks was reflected on social media during the pandemic period of 2020. We examined Instagram posts associated with a sample of eight urban parks in Bucharest, Romania and also the entire history of Google reviews between January and August 2020. The selection of parks was made according to their size, location in Bucharest, previous reported number of visitors and profile of attractiveness. Results revealed that the peak period of the COVID-19 pandemic and the first initiation of the lockdowns strongly affected the recreation and leisure activities that people performed almost daily in the parks of Bucharest. Reviews and comments of the population were not that focused on the pandemic even after the restrictions were lifted, but they evidenced the positive and negative aspects of each park. Our results can represent a useful instrument for local administrations in determining both the flow of visitors but also their perceptions towards the endowments, landscape and most important management of urban parks.

Exploring public values through Twitter data associated with urban parks pre- and post- COVID-19

“…As expected, values associated with urban parks after March 2020 are reflecting the experiences and opinions regarding the global public crisis. The new theme regarding “the social distancing norm” ( Collignon, 2021 ) emerging from Twitter conversations indicated how the pandemic has influenced park use, such as topics about wearing masks, social distancing, and the stay at home order ( Grzyb et al, 2021 , Niță et al, 2021 ). Interestingly, this change varied across study parks.…”

“…Another novelty of our analytic approach was investigating the tones of the tweets associated with each value theme based on the Twitter “messages.” This could not have been achieved simply by examining keywords or hashtags in social media posts ( Grzyb et al, 2021 , Niță et al, 2021 ). The application of sentiment analysis on Twitter messages associated with specific value topics provide a systematic way to further examine the nuances of the tweets for each theme.…”

“…Through a content analysis of Instagram hashtags about urban parks in Poland, Grzyb et al (2021) discovered more forms of recreation and an increasing trend in nature and wilderness appreciation in urban greenspaces during the pandemic, compared to 2019. Niță et al (2021) investigated recreational and social values delivered by parks during the pandemic. They used activity-related keywords highlighted in Instagram posts in urban parks in Bucharest, Romania.…”

A reliability study of the Park Life public participatory geographic information system survey

“…For example, some studies have examined park use based on the count and visual content of photographs geolocated within parks (Donahue et al, 2018; Hamstead et al, 2018; Sessions et al, 2016; Song et al, 2020). Others have analysed the language of social media posts (Instagram), reviews posted of urban parks on Google (Niță et al, 2021; Park et al, 2022), and Twitter [X] posts relevant to park and nature experiences and recreational activities (Park et al, 2022).…”

COVID-19 pandemic changes the recreational use of Moscow parks in space and time: Outcomes from crowd-sourcing and machine learning

“…Moreover, when applied together with advanced technologies, such as image detection by machine-learning, analysis of large datasets becomes less labor-intensive, and allows assessing spatial variability and temporal changes in recreational use and activities of urban green spaces ( Bubalo et al, 2019 , Levin et al, 2017 , Richards and Friess, 2015 ). For example, Niță et al (2021) collected and analyzed Instagram posts for various parks in Buckarest (Romania) demonstrating patterns of number of photos while focusing on text analysis done by manual coding. Huang et al (2022) investigated how public values associated with New York City parks has shifted between pre- COVID (i.e., from March 2019 to February 2020) and post- COVID (i.e., from March 2020 to February 2021) using a short modelling technique on Twitter posts.…”