Today we are awash with data, especially when it comes to studying cities from a diverse data ecosystem ranging from demographic to remotely sensed imagery and social media. This has led to the growth of urban analytics providing new ways to conduct quantitative research within cities. One area that has seen significant growth is using natural language processing techniques on text data from social media to explore various issues relating to urban morphology. However, we would argue that social media only provides limited insights when dealing with longer-term urban phenomena, such as the growth and shrinkage of cities. This relates to the fact that social media is a relatively recent phenomenon compared to longer-term urban problems that take decades to emerge. Concerning longer-term coverage, newspapers, which are increasingly becoming digitized, provide the possibility to overcome the limitations of social media and provide insights over a timeframe that social media does not. To demonstrate the utility of newspapers for urban analytics and to study longer-term urban issues, we utilize an advanced topic modeling technique (i.e., BERTopic) on a large number of newspaper articles from 1975 to 2021 to explore urban shrinkage in Detroit. Our topic modeling results reveal insights related to how Detroit shrinks. For example, side effects of 2007 to 2009 economic recessions on Detroit’s automobile industry, local employment status, and the housing market.
AduPDelmelleEC (2022) Spatial variations in exclusionary criteria from online rental advertisements. The Professional Geographer74(4): 704–714.
2.
AllaouiMKherfiMLCherietA (2020) Considerably improving clustering algorithms using UMAP dimensional- ity reduction technique: a comparative study. In: Image and Signal Processing. Cham: Springer International Publishing, 317–325.
3.
BattyM (2019) Urban analytics defined. Environment and Planning B: Urban Analytics and City Science46(3): 403–405.
BrochierRGuilleAVelcinJ (2019) Global vectors for node representations. In: WWW ’19: The Web Conference, San Francisco, CA, USA, 13–17 May 2019, New York, NY, USA: Association for Computing Machinery, 2587–2593.
6.
CampelloRJMoulaviDSanderJ (2013) Density-based clustering based on hierarchical density estimates. In: Advances in Knowledge Discovery and Data Mining: 17th Pacific-Asia Conference, PAKDD 2013, Proceedings, Part II 17, Gold Coast, Australia, 14–17 April 2013, Heidelberg: Springer Berlin, 160–172.
7.
ChappleKPoorthuisAZookM, et al. (2022) Monitoring streets through tweets: using user-generated geographic information to predict gentrification and displacement. Environment and Planning B: Urban Analytics and City Science49(2): 704–721.
8.
ChawatheSS (2020) Topic analysis of climate-change news. 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 06–08 January 2020, IEEE, 0543–0549.
9.
ChenQCrooksA (2022) Analyzing the vaccination debate in social media data pre- and post-COVID-19 pandemic. International Journal of Applied Earth Observation and Geoinformation110: 102783.
10.
CroitoruAWayantNCrooksA, et al. (2015) Linking cyber and physical spaces through community detection and clustering in social media feeds. Computers, Environment and Urban Systems53: 47–64.
11.
DemyanykYVan HemertO (2011) Understanding the subprime mortgage crisis. Review of Financial Studies24(6): 1848–1880.
12.
DuMWangLZouS, et al. (2018) Modeling the census tract level housing vacancy rate with the Jilin1-03 satellite and other geospatial data. Remote Sensing10(12): 1920.
13.
DunnMBlankA (2018) Job Market Continued to Improve in 2017 as the Unemployment Rate Declined to a 17-year Low: Monthly Labor Review: U.S. Bureau of Labor Statistics. Technical Report. Washington, DC: U.S. Bureau of Labor Statistics.
14.
EggerRYuJ (2022) A topic modeling comparison between LDA, NMF, Top2Vec, and BERTopic to demystify Twitter posts. Frontiers in Sociology7: 886498.
15.
FriedmanMGrawertACCullenJ (2017) Crime Trends, 1990- 2016. New York, NY: Brennan Center for Justice at New York University School of Law.
16.
GoodmanCJManceSM (2011) Employment Loss and the 2007-09 Recession: An Overview. Technical Report. Washington, DC: U.S. Bureau of Labor Statistics.
17.
GrootendorstM (2022) Bertopic: Neural Topic Modeling with a Class-Based TF-IDF Procedure. DOI: 10.48550/arXiv.2203.05794.
18.
HanSYTsouMHKnaapE, et al. (2019) How do cities flow in an emergency? tracing human mobility patterns during a natural disaster with big data and geospatial data science. Urban Science3(2): 51.
19.
KherwaPBansalP (2020) Topic modeling: a comprehensive review. EAI Endorsed Transactions on Scalable Information Systems7(24).
20.
KhuranaDKoliAKhatterK, et al. (2023) Natural language processing: state of the art, current trends and challenges. Multimedia Tools and Applications82(3): 3713–3744.
21.
KoroteevMV (2021) BERT: A Review of Applications in Natural Language Processing and Understanding. DOI: 10.48550/arXiv.2103.11943.
22.
LevinDP (1992) Chrysler Opens Plant, Makes a Point. Technical Report. The New York Times (accessed 1 April 1992).
LiYXieY (2018) A new urban typology model adapting data mining analytics to examine dominant trajectories of neighborhood change: a case of metro Detroit. Annals of the American Association of Geographers108(5): 1313–1337.
25.
LindstedtNC (2019) Structural topic modeling for social scientists: a brief case study with social movement studies literature, 2005–2017. Social Currents6(4).
26.
LongYHuangC (2019) Does block size matter? the impact of urban design on economic vitality for Chinese cities. Environment and Planning B: Urban Analytics and City Science46(3): 406–422.
27.
LongYWuK (2016) Shrinking cities in a rapidly urbanizing China. Environment and Planning A: Economy and Space48(2): 220–222.
28.
LuoSHeSY (2021) Using data mining to explore the spatial and temporal dynamics of perceptions of metro services in China: the case of Shenzhen. Environment and Planning B: Urban Analytics and City Science48(3): 449–466.
29.
McDonaldJF (2014) What happened to and in Detroit?Urban Studies51(16): 3309–3329.
30.
MengXLongY (2022) Shrinking cities in China: evidence from the latest two population censuses 2010–2020. Environment and Planning A: Economy and Space54(3): 449–453.
31.
MikolovTChenKCorradoG, et al. (2013) Efficient Estimation of Word Representations in Vector Space. DOI: 10.48550/arXiv.1301.3781.
32.
NeillWJV (2015) Carry on shrinking? the bankruptcy of urban policy in Detroit. Planning Practice and Research30(1): 1–14.
33.
NilssonIDelmelleEC (2023) An embedding-based text classification approach for understanding micro-geographic housing dynamics. International Journal of Geographical Information Science1–27.
34.
ParkYKimMSeongK (2021) Happy neighborhoods: investigating neighborhood conditions and sentiments of a shrinking city with Twitter data. Growth and Change52(1): 539–566.
35.
PedregosaFVaroquauxGGramfortA, et al. (2011) Scikit-learn: machine learning in Python. Journal of Machine Learning Research12: 2825–2830.
36.
PhilpD (2017) A $500 House in Detroit: Rebuilding an Abandoned Home and an American City. New York, NY: Simon & Schuster.
37.
PlunkertLHaygheH (1995) Strong Employment Gains Continue in 1994: Monthly Labor Review. U.S. Bureau of Labor Statistics.
38.
PoethigESchillingJGoodmanL, et al. (1964) The Detroit housing Market: Challenges and Innovations for a Path Forward. Washington DC: Urban Institute.
39.
ReadesJWilliamsJ (2023) Clustering and Visualising Documents Using Word Embeddings. Programming Historian.
40.
ReidNCarrollMCYeX (2013) The great recession of 2007- 2009. Economic Development Quarterly27(2): 87–89.
41.
ReimersNGurevychI (2020) Making monolingual sentence embeddings multilingual using knowledge distillation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Online. Association for Computational Linguistics, 4512–4525.
42.
SandhiyaRBoopikaAMAkshathaM, et al. (2022) A review of topic modeling and its spplication. In: Singh ManshahiaMKharchenkoVMunapoE, et al. (eds), Handbook of Intelligent Computing and Optimization for Sustainable Development. John Wiley & Sons, Ltd, 305–322.
43.
SilvermanRMYinLPattersonKL (2013) Dawn of the dead city: an exploratory analysis of vacant addresses in Buffalo, NY 2008–2010. Journal of Urban Affairs35(2): 131–152.
44.
TranMDraegerCWangX, et al. (2022) Monitoring the well-being of vulnerable transit riders using machine learning based sentiment analysis and social media: lessons from COVID-19. Environment and Planning B: Urban Analytics and City Science50(1): 60–75.
45.
WangZYeXTsouMH (2016) Spatial, temporal, and content analysis of Twitter for wildfire hazards. Natural Hazards83(1): 523–540.
46.
WangQXinZNiuF (2022) Analysis of the spatio-temporal patterns of shrinking cities in China: evidence from nighttime light. Land11(6): 871.
47.
WeaverRBagchi-SenSKnightJ, et al. (2016) Shrinking Cities: Understanding Urban Decline in the United States. London: Routledge.
48.
XieYGongHLanH, et al. (2018) Examining shrinking city of Detroit in the context of cocio-spatial inequalities. Landscape and Urban Planning177: 350–361.
49.
ZhangWBarchersCSmith-ColinJ (2022) Transit communication via Twitter during the COVID-19 pandemic. Environment and Planning B: Urban Analytics and City Science23998083221135609.
50.
ZhouYLiCMaZ, et al. (2019) Identification of shrinkage and growth patterns of a shrinking city in China based on nighttime light data: a case study of Yichun. Sustainability11(24): 6906.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
