Leveraging Social Media to Track Urban Park Quality for Improved Citizen Health
In this chapter, we showcase the use of qualitative data available on two “geobrowsers” (i.e., Google Maps and Foursquare) and of a data-mining technique to quantify the sentiment of online reviews about parks. The underlying interest for this study comes from the growing literature suggesting that living near parks or other open spaces contributes to higher levels of physical activity and to lower levels of stress and fewer mental health problems. Mecklenburg County (North Carolina), which encompasses the City of Charlotte, is used as a case study. In a comparison among 97 cities in the USA, The Trust for Public Land ranks Charlotte’s park system at the very bottom and reports their spending per resident on their park system among the lowest 20% of these cities. Considering their lower spending, the city government may be particularly interested to leverage publicly available data from social media to complement the assessments they already perform about their park system, such as satisfaction surveys or quality assessments. Nevertheless, Charlotte’s low ranking – although unfortunate – indicates an opportunity for the city to improve its park system, which in turn could engage residents in more physical activity and, in doing so, create positive community health outcomes.
KeywordsParks Social media Charlotte NC Sentiment analysis Online reviews Urban health
- Crampton, J., & others. (2013). Beyond the Geotag: Situating ‘big data’ and leveraging the potential of the GeoWeb. Cartography and Geographic Information Science, 40(2), 130–139.Google Scholar
- DHHS, United States. Department of Health. (2008). Physical Activity Guidelines for Americans: Be Active, Healthy, and Happy! (Vol. 36). Government Printing Office, Washington, DC.Google Scholar
- Fekete, E. (2017). Foursquare in the city of fountains: Using Kansas City as a case study for combining demographic and social media data. In Thatcher, J., Eckert J., and A. Shears (Eds.), Thinking big data in geography: New regimes, new research, (pp. 165–88). University of Nebraska Press, Lincoln, NE, USA.Google Scholar
- Fekete, E., & Warf, B. (2013). Information technology and the “Arab Spring”. The Arab World Geographer, 16(2), 210–227.Google Scholar
- Garcia Esparza, S., O’Mahony, M. P., & Smyth, B. (2010, September). On the real-time web as a source of recommendation knowledge. In Proceedings of the fourth ACM conference on recommender systems (RecSys '10), Barcelona, Spain (pp.305-308). Association for Computing Machinery, New York, NY. https://doi.org/10.1145/1864708.1864773.
- Lopez, R. P., & Hynes, H. P. (2006). Obesity, physical activity, and the urban environment: Public health research needs. Environmental Health, 5(25). https://doi.org/10.1186/1476-069X-5-25.
- MCDH, Mecklenburg County Department of Health. (2016) 2015 Mecklenburg County State of the Country Health Report, Mecklenburg County Department of Health, Health Statistics and Epidemiology. Available at: charmeck.org/mecklenburg/county/HealthDepartment/HealthStatistics
- Moon, G., & Gillespie, R. (1995). Society and health: An introduction to social science for health professionals. Routledge, London, UK. ISBN-13: 978-0415110228.Google Scholar
- Morstatter, F., Pfeffer, J., Liu, H., & Carley, K. M. (2013, July). Is the sample good enough? comparing data from twitter’s streaming API with Twitter’s Firehose. In Seventh international AAAI conference on weblogs and social media, Cambridge, MA, USA (pp. 400-408). Association for the Advancement of Artificial Intelligence, Palo Alto, CA, USA. https://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/view/6071/6379.
- Mueller, N., Rojas-Rueda, D., Basagaña, X., Cirach, M., Cole-Hunter, T., Dadvand, P., et al. (2016). Urban and transport planning related exposures and mortality: A health impact assessment for cities. Environmental Health Perspectives, 125, 89–96. https://doi.org/10.1289/EHP220.CrossRefGoogle Scholar
- Nielsen, F. A. (2011). A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. In Proceedings of the EWSC2011 workshop on ‘Making Sense of Microposts’: Big things come in small packages, Heraklion, Greece. (pp. 93–98). https://arxiv.org/abs/1103.2903.
- Parks, S. E., Housemann, R. A., & Brownson, R. C. (2003). Differential correlates of physical activity in urban and rural adults of various socioeconomic backgrounds in the United States. Journal of Epidemiology and Community Health, 57, 29–35. https://doi.org/10.1136/jech.57.1.29.CrossRefGoogle Scholar
- Paul, M. J., & Dredze, M. (2011, July). You are what you Tweet: Analyzing Twitter for public health. In The Fifth International AAAI Conference on Weblogs and Social Media (ICWSM-11), Barcelona, Spain, (pp. 265–272). Association for the Advancement of Artificial Intelligence, Palo Alto, CA, USA. https://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/view/2880/3264.
- Pew Internet Research. (2018). Social media fact sheet. Available at: http://www.pewinternet.org/fact-sheet/social-media/. Accessed 31 July 2018.
- Physical Activity Council. (2016). 2016 participation report. Available at: physicalactivitycouncil.com. Accessed 20 May 2016.
- Rainie, L. (2018). Americans’ complicated feelings about social media in an era of privacy concerns. Pew Internet Research. Available at: http://www.pewresearch.org/fact-tank/2018/03/27/americans-complicated-feelings-about-social-media-in-an-era-of-privacy-concerns/. Accessed 31 July 2018.
- TPL, Trust for Public Land. (2010). The economic benefits of the park and recreation system of Mecklenburg County, North Carolina. Available at: tpl.org/charlottemecklenburg-county-park-value-report. Accessed 15 Mar 2014.
- TPL, Trust for Public Land. (2016). ParkScore index. Available at: parkscore.tpl.org. Accessed 16 May 2016.
- Wilson, T., Wiebe, J., & Hoffmann, P. (2005, October). Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the conference on human language technology and empirical methods in natural language processing (HLT'05), Vancouver, Canada (pp. 347–354). Association for Computational Linguistics, Stroudsburg, PA, USA. https://doi.org/10.3115/1220575.1220619.