The Geography of Happiness: Connecting Twitter Sentiment and Expression, Demographics, and Objective Characteristics of Place

By Lewis Mitchell, Kameron Decker Harris, Morgan R. Frank, Peter Sheridan Dodds, Christopher M. Danforth. PLoS ONE, 2013

510 citations recorded by the source corpus.

We conduct a detailed investigation of correlations between real-time expressions of individuals made across the United States and a wide range of emotional, geographic, demographic, and health characteristics. We do so by combining (1) a massive, geo-tagged data set comprising over 80 million words generated in 2011 on the social network service Twitter and (2) annually-surveyed characteristics of all 50 states and close to 400 urban populations. Among many results, we generate taxonomies of states and cities based on their similarities in word use; estimate the happiness levels of states and cities; correlate highly-resolved demographic characteristics with happiness levels; and connect word choice and message length with urban characteristics such as education levels and obesity rates. Our results show how social media may potentially be used to estimate real-time levels and changes in population-scale measures such as obesity rates.

Subfields: Health, Statistical and Nonlinear Physics, Transportation

View Paper: https://www.semanticscholar.org/paper/06046e872b3d93b919732f0f3d17a4857f5d05a8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Health

In Statistical and Nonlinear Physics

In Transportation

Citations in the corpus

Population Bias in Geotagged Tweets (2015, background): “• emotion (Mitchell et al. 2013), and • social ties (Stephens and Poorthuis 2014; Takhteyev, Gruzd, and Wellman 2012; Cho, Myers, and Leskovec 2011).”
Predicting Factuality of Reporting and Bias of News Media Sources (2018, background): “…and features for clickbait title classiﬁcation from (Chakraborty et al., 2016); • Sentiment : sentiment scores using lexicons (Recasens et al., 2013; Mitchell et al., 2013) and full systems (Hutto and Gilbert, 2014); • Engagement : number of shares, reactions, and comments on Facebook; •…”
Natural language processing in mental health applications using non-clinical texts† (2017, methodology): “…example, Schwartz et al. (2013) and Larsen et al. (2015) compare against surveys of life satisfaction, De Choudhury et al. (2013b) use depression incidence and prescription rates for antidepressants, and Mitchell et al. (2013) compare against gun violence, wealth, obesity and several other indexes.”
Geo-located Twitter as proxy for global mobility patterns (2013, background): “Recently, this research was done also with a geographic perspective (Frank et al. 2013; Mitchell et al. 2013).”
Climate Change Sentiment on Twitter: An Unsolicited Public Opinion Poll (2015, unknown): “Since its development, the hedonometer has been implemented in studies involving the happiness of cities and states [30], the happiness of the English language as a whole [21], and the relationship between individuals’ happiness and that of those they connect with [4].”
Detecting depression and mental illness on social media: an integrative review (2017, background): “Examples of features included in the different feature sets referenced in Tab Assessment by Mechanical Turk [39].”
Like It or Not (2016, background): “For example, it is possible to explore how geographic places or meteorological variables and events inﬂuence the level of happiness within a society [Mitchell et al. 2013; Curini et al. 2014].”
Communities in Action: Pathways to Health Equity (2017, methodology): “…with global warming and climate change (Lineman et al., 2015) and the moods of patients in online cancer communities (Rodrigues et al., 2016), and it has been used in the “Geography of Happiness” in combination with demographics and objective characteristics of place (Mitchell et al., 2013).”
Diffusion of Lexical Change in Social Media (2012, background): “A wave of recent research has shown how social media datasets can enable large-scale analysis of patterns of communication [10,11], sentiment [12–14], and influence [15–19].”
Rapid assessment of disaster damage using social media activity (2016, background): “Sentiment in Twitter has been studied and demonstrated to reflect temporal (19, 70) and geographical (71) mood variations.”
The Geography and Importance of Localness in Geotagged Social Media (2016, background): “[32] what can occur if non-local VGI is filtered out of these studies.”
Analyzing the correlation between visual space and residents' psychology in Wuhan, China using street-view images and deep-learning technique (2021, unknown): “The urban space environment affects residents ’ perceptions and is closely related to people ’ s depression and happiness [1,2].”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, background): “Twitter sentiment analysis is one such application where conditioning on these variables is prevalent (Mitchell et al., 2013; Vosoughi et al., 2015; Volkova et al., 2013).”