Volume 37 - Article 46 | Pages 1477–1514

Using Twitter data for demographic research

By Dilek Yildiz, Jo Munson, Agnese Vitali, Ramine Tinati, Jennifer A. Holland

Print this page  Facebook  Twitter

 

 
Date received:24 Dec 2016
Date published:22 Nov 2017
Word count:10233
Keywords:calibration, population estimates, social media, Twitter
DOI:10.4054/DemRes.2017.37.46
 

Abstract

Background: Social media data is a promising source of social science data. However, deriving the demographic characteristics of users and dealing with the nonrandom, nonrepresentative populations from which they are drawn represent challenges for social scientists.

Objective: Given the growing use of social media data in social science research, this paper asks two questions: 1) To what extent are findings obtained with social media data generalizable to broader populations, and 2) what is the best practice for estimating demographic information from Twitter data?

Methods: Our analyses use information gathered from 979,992 geo-located Tweets sent by 22,356 unique users in South East England between 23 June and 4 July 2014. We estimate demographic characteristics of the Twitter users with the crowd-sourcing platform CrowdFlower and the image-recognition software Face++. To evaluate bias in the data, we run a series of log-linear models with offsets and calibrate the nonrepresentative sample of Twitter users with mid-year population estimates for South East England.

Results: CrowdFlower proves to be more accurate than Face++ for the measurement of age, whereas both tools are highly reliable for measuring the sex of Twitter users. The calibration exercise allows bias correction in the age-, sex-, and location-specific population counts obtained from the Twitter population by augmenting Twitter data with mid-year population estimates.

Contribution: The paper proposes best practices for estimating Twitter users’ basic demographic characteristics and a calibration method to address the selection bias in the Twitter population, allowing researchers to generalize findings based on Twitter to the general population.

Author's Affiliation

Dilek Yildiz - Wittgenstein Centre for Demography and Global Human Capital (IIASA, VID/ÖAW, WU), Austria [Email]
Jo Munson - University of Southampton, United Kingdom [Email]
Agnese Vitali - University of Southampton, United Kingdom [Email]
Ramine Tinati - University of Southampton, United Kingdom [Email]
Jennifer A. Holland - Erasmus Universiteit Rotterdam, Netherlands [Email]

Other articles by the same author/authors in Demographic Research

» The timing of marriage vis-à-vis coresidence and childbearing in Europe and the United States
Volume 36 - Article 20

» Who brings home the bacon? The influence of context on partners' contributions to the household income
Volume 35 - Article 41

» Youth prospects in a time of economic recession
Volume 29 - Article 36

» Love, marriage, then the baby carriage? Marriage timing and childbearing in Sweden
Volume 29 - Article 11

Similar articles in Demographic Research

» WhatsApp usage patterns and prediction of demographic characteristics without access to message content
Volume 39 - Article 22    | Keywords: social media

» Estimates of mortality and population changes in England and Wales over the two World Wars
Volume 13 - Article 16    | Keywords: population estimates

» Official population statistics and the Human Mortality Database estimates of populations aged 80+ in Germany and nine other European countries
Volume 13 - Article 14    | Keywords: population estimates

» The Survivor Ratio Method for Estimating Numbers at High Ages
Volume 6 - Article 1    | Keywords: population estimates