North Carolina State University researchers found they could use Twitter to understand differences in what New York City park users valued most about four iconic city parks before and after the COVID lockdowns went into effect -19. Researchers also found Twitter useful for tracking complaints about individual parks.
Findings indicate that social media can be an important tool for park managers, park planners, or others to respond in real time to changes in user needs or to plan future parks, potentially faster than using traditional survey-based methods.
“We found that you can extract details about individual parks as well as track what people value in the parks, the complaints they have about specific events and even the broader social issues people are talking about,” said co-author study Aaron Hipp. associate professor of community health and sustainability at NC State. “While we have some additional work to do to automate this and get closer to real-time monitoring, we think our findings show that parks can monitor this information and feel confident that a portion of social media traffic can be a fairly reliable reflection of public sentiment. “
For the study, researchers tracked tweets about Central Park in Manhattan, Prospect Park in Brooklyn, Flushing Meadows in Queens, and Bronx Park from March 2019 to February 2020 and then from March 2020 to February 2021. They used natural language processing and topic modeling techniques to analyze a total of 71,792 tweets, which excluded retweets, influencer tweets, bots, and tweets containing less than three words. Overall, they found that tweets about Central Park increased by 18% and tweets about Prospect Park increased by 87%. Meanwhile, tweets about Flushing Meadows dropped 71% and tweets about Bronx Park dropped 32%.
The researchers said the findings reflect the effects of a COVID-19 stay-at-home order. As outdoor recreation was limited to solitary exercise, parks and trails became popular destinations after March 2020. However, this trend did not seem to hold true in all parks due to their unique offerings.
“Flushing Meadows is famous for sporting events, but during the pandemic, they were mostly canceled,” said lead study author Jing-Huei Huang, a postdoctoral research fellow at NC State. “In Bronx Park, people tended to tweet about the zoo and the Botanic Garden, but they were closed, so that was reflected in the drop in tweets.”
Tweets about physical activity such as walking, running and cycling increased in all four parks during the pandemic. The researchers also saw concerns about social distancing and related issues in all four.
“In all four parks, we saw that participating in outdoor physical activity was especially important when people had to stay apart and they were unable to participate in social activities,” Huang said. “We were also able to capture negative sentiment when people were upset by seeing crowds in parks, or when people didn’t wear masks,” Huang added. “It’s sending useful signals to the management team.”
They also captured tweets about specific incidents in each park that reflected larger social concerns. For example, they saw a spike in tweets about racial discrimination in May 2020 after the birdwatching incident in Central Park, when Amy Cooper, a white woman, called the police about a black man, Christian Cooper, who was birdwatching birds. They also saw complaints that Flushing Meadows became a “giant parking lot” amid advocacy for a new greenway to increase access and ensure pedestrian safety.
In a follow-up study, they are planning to compare data collected using traditional surveys with what they found on social media.
“A long-term goal is to be able to get this feedback in real time so that park managers can initiate programming in response,” Hipp said. “For example, amid a spike in demand, you could open a nearby wake or bike path. There is also great potential here for evaluating programs and events especially when decisions are made immediately, such as during COVID. This social media data can provide a retrospective opportunity to gauge what people were saying about the park, a specific program or event.”
The paper, “Exploring values through Twitter data related to urban parks before and after COVID-19,” was published online at Landscape and Urban Planning. Co-authors included Myron F. Floyd and Laura G. Tateosian. The study is part of the project “Characteristics of green space and their links to population health” funded by USDA Forest Service Grant/Agreement Number: 16-JV-11330144-065
– shoulder –
Note to authors: Abstract follows.
“Exploring values through Twitter data related to urban parks before and after COVID-19”
authors: Jing-Huei Huang, Myron F. Floyd, Laura G. Tateosian, and J. Aaron Hipp
Published online at Landscape and Urban Planning.
DOI: 10.1016/j.landurbplan.2022.104517
abstract: Since the closure of schools and businesses due to the emerging COVID-19 outbreak, urban parks have been a popular destination, providing spaces for daily fitness activities and an escape from the home environment. Evidence is needed for parks and recreation departments and agencies to base decisions on when adapting policies in response to rapidly changing demand and preferences during the pandemic. Applying social media data analytics techniques allows a qualitative and quantitative approach to big data to gain unobtrusive and immediate insights into how parks are rated. This study investigates how public values associated with NYC parks have shifted between pre-COVID (ie, from March 2019 to February 2020) and post-COVID (ie, from March 2020 to February 2021) through a media microblogging platform social -Twitter. A topic modeling technique for short text identified common features of changes in Twitter topics related to impressions and values related to parks over two years. While NYC’s lockdown resulted in far fewer social activities in parks, some parks continued to be valued for physical activity and contact with nature during the pandemic. Concerns about people not maintaining physical distance were raised in parks where frequent human interactions and crowding appeared to cause a higher probability of coronavirus transmission. This study shows that social media data can be used to capture park values and be park-specific. Results can inform park management during outages when use changes and public needs may change.
