EXAMINING ASSOCIATIONS OF THE SOCIOECONOMIC CHARACTERISTICS WITH THE NUMBER OF GEO-TAGGED TWEETS IN CENSUS BLOCK LEVEL (CASE STUDY: BOSTON)

Abstract. In this study, the aim is to help uncover some facts about who the Twitter users really are. To this purpose, geotagged twitter data from the city of Boston together with socio-economic data were used. In the first step, tweets in each census block were counted and using the Getis-Ord Gi* index the hotspots and coldspots of tweet locations were extracted. Then, a multiple linear regression was employed, having the number of tweets as the response variable and the population data, age, education, occupation and income as the explanatory variables. Hence, more insight into the relationship between the number of tweets and some socio-economic factors is obtained. Results show that the central parts of Boston are the hotspot and the southern areas are the coldspot locations with regard to tweet numbers. The regression results imply that the number of tweets shared by users in an area is related to the income, the number of people having a university degree and the number of people having each type of job in that spatial unit. The results achieved in this paper could lead to a better vision and understanding in analyzing the tweeter users’ behavior in any area of research and application.