Abstract
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.
Highlights
Today, social networks have gained enormous popularity as a medium to communicate and share contents
Geo-tagged tweets, by sharing location alongside the content makes it possible to analyze the twitter data regarding a spatial point of view
A 4-month geo-tagged twitter data of Boston city was used, and by utilizing the geographic locations of the tweets, the hotspot maps were produced that visualizes the areas in which the number of tweets was higher than their neighboring areas
Summary
Social networks have gained enormous popularity as a medium to communicate and share contents. Researchers have previously tried to estimate demographic characteristics of Twitter users based on their tweets and other public data such as their Twitter profiles (Mislove et al, 2011; Pennacchiotti and Popescu, 2011; Rao et al, 2010; Sloan et al, 2013) Looking at the tweets’ locations puts forward the idea that their distribution is heterogeneous. Such a distribution is the result of a spatial process affected by environmental parameters which cause the considered phenomena not to follow a uniform distribution. The study concluded that the nonrepresentative characteristics of Twitter users indicate that using Twitter data for research where representativeness is important, such as predicting elections is inappropriate (Blank, 2017). Sloan and Morgan (2015) have concluded in their study that there are statistically significant differences in demographic characteristics of the people using geo-services and the people
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
