Wikipedia traffic data and electoral prediction: towards theoretically informed models

Our results section is divided into three parts. First, we look at the relationship between Wikipedia traffic patterns around election time and overall electoral turnout. Then, we develop a model to try and predict absolute vote share outcomes for different political parties. Finally, we look at whether such a model can be developed for changes in vote share. We will begin by looking at the relationship between overall levels of traffic to the general political articles in different language editions of Wikipedia and electoral turnout. These articles offer general information about the election, such as the date on which it will be held. As we highlight in our theory section we expect that more people looking at this page indicates that higher levels of people are interested in voting in…


Link to Full Article: Wikipedia traffic data and electoral prediction: towards theoretically informed models