The internet usage rate in Turkey: a machine learning approach

Abstract

Most studies on measuring coverage bias in internet surveys use internet access as a critical measurement variable. However, access to the internet does not mean that individuals are using it. Therefore, using the internet usage rate as a key variable is crucial to get an accurate overview of the internet coverage of a population. This study closes these gaps by using a better indicator for measuring the internet usage rate. It is the first study measuring the internet usage rate in Turkey by using the real internet usage rate of the population and applying a machine learning algorithm. The results exposed significant differences in socio-demographic characteristics when internet users were compared with non-users. Furthermore, the coverage bias associated with internet users remained different for several demographic categories. The results of web-based surveys based on the actual internet usage rate are crucial for the scientific community and marketers.