Language, demographics, emotions, and the structure of online social networks

Abstract

Social networks affect individuals' economic opportunities and wellbeing. However, few of the factors thought to shape networks-culture, language, education, and income-were empirically validated at scale. To fill this gap, we collected a large number of social media posts from a major US metropolitan area. By associating these posts with US Census tracts through their locations, we linked socioeconomic indicators to group-level signals extracted from social media, including emotions, language, and online social ties. Our analysis shows that tracts with higher education levels have weaker social ties, but this effect is attenuated for tracts with high ratio of Hispanic residents. Negative emotions are associated with

Common Core State Standards on Twitter: Public Sentiment and Opinion Leaders

“…In this study, the sentiment of each of the 264,038 tweets with meaningful geolocations in the Common Core corpus was analyzed using SentiStrength. Among many sentiment analysis tools, SentiStrength was chosen because prior literature has consistently shown its high validity for tweet sentiment detection based on a lexicon-based method (Abbasi, Hassan, & Dhar, 2014; Gonçalves, Araújo, Benevenuto, & Cha, 2013; Lerman, Arora, Gallegos, Kumaraguru, & Garcia, 2016; Lopes, Pinto, & Francisco, 2016; Pfitzner, Garas, & Schweitzer, 2012; Stieglitz & Dang-xuan, 2013; Witherspoon & Stone, 2013). In particular, SentiStrength is considered to be by far one of the best unsupervised tool to analyze the sentiment expressed in tweets (Abbasi et al, 2014).…”

Technological and social networks of a pastoralist artificial society: agent-based modeling of mobility patterns

“…Fig. 4 Opening the social dimension [20,50], metabolism [1,4], and vision [1,20] Family: all in their vision Trustworthiness: 90%;…”

“…Family members are reliable and trustworthy sources of information, since communication with them is among the most effective. Also, the stronger the emotional bonds, the easier it is to maintain them over long distances [19,37,44,50]. Furthermore, obligations to family members are long-lasting and thus have a significant impact on mobility.…”

Analyzing the association between emotions and socioeconomic characteristics of census tracts via user‐generated content

“…Recent decades have witnessed a surge in scientific research on human emotions, especially happiness, based on work in social psychology (Ashkanasy & Humphrey, 2011; Lerman et al, 2018; Singh, Atrey, & Hegde, 2017), epidemiology (Mitchell, Frank, Harris, Dodds, & Danforth, 2013), economics (Abdullah, Murnane, Costa, & Choudhury, 2015), and especially human geography, in which one of the core research objectives is to analyze the correlation between human emotions and the living environment (Davidson & Milligan, 2007; Gallegos, Lerman, Huang, & Garcia, 2016; Jian, Zhen, Xi, & Zhai, 2016; Kang et al, 2019).…”

“…There is a huge amount of personal emotional information hidden in social media platforms in the form of text and images, and this information can be mined by emerging social computing tools. When this information is geotagged, emotional‐geographical studies can take advantage of this new data to work at different spatial scales, ranging from the census tract (Lerman et al, 2018; Svoray, Dorman, Shahar, & Kloog, 2018) to the urban scale (Gallegos et al, 2016) and the national scale (Office for National Statistics, 2019; Zheng et al, 2019). At the same time, machine learning, especially deep learning technology, has made it possible to extract human emotions from textual data with natural language processing (Ballatore & Adams, 2015; Bertrand et al, 2013; Mitchell et al, 2013; Zheng et al, 2019) and from image data with cognitive recognition algorithms (Kang et al, 2019; Singh et al, 2017; Xu, Wang, Li, & Yu, 2017; Yu & Zhang, 2015).…”