Happy neighborhoods: Investigating neighborhood conditions and sentiments of a shrinking city with Twitter data

Yunmi Park, Minju Kim, Kijin Seong

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


Planning interventions have been applied to improve the well-being, hereafter happiness, of residents. The happiness in shrinking cities, in particular, becomes more critical since urban decline tends to induce an unequal and uneven distribution of care under a limited budget and human resources. Using geo-tagged Twitter, census, and geospatial data on Detroit, Michigan, which is one of the well-known shrinking cities in the U.S., the spatial distribution of sentiments, topics of tweets appeared, and the association between neighborhood conditions and the level of happiness were examined. The outcomes indicate that people in Detroit are posting happy tweets more than negative tweets. The downtown area holds both positive and negative hotspots, which are clustered around sports arenas and bars, respectively. Neighborhoods with young and well-educated residents, situated close to amenities (i.e., recreation facilities, colleges, and commercial areas), and less crime tend to be happier. The use of SNS data could serve as a meaningful social listening tool to reconcile the declining urban vitality of neighborhoods since people interact with those spaces. Negative sentiments are attached to specific neighborhoods with certain conditions so that regeneration efforts should take place in neighborhoods with a higher priority.

Original languageEnglish
Pages (from-to)539-566
Number of pages28
JournalGrowth and Change
Issue number1
StatePublished - Mar 2021

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NSF) grant funded by the Korea government (MSIT) (No. 2020R1C1C1008867).

Publisher Copyright:
© 2020 Wiley Periodicals LLC.


Dive into the research topics of 'Happy neighborhoods: Investigating neighborhood conditions and sentiments of a shrinking city with Twitter data'. Together they form a unique fingerprint.

Cite this