Big Social Data Analytics in Football: Predicting Spectators and TV Ratings from Facebook Data

This paper explores the predictive power of bigsocial data in regards to football fans’ off-line and on-linebehaviours. We address the research question of to what extentcan big social data from Facebook predict the numberof spectators and TV ratings in the case of Danish NationalFootball Association (DBU). The predictive model was built fromFacebook, match attendance, and TV ratings data sets from 2014-2016. The best fit was a linear regression model with GLM coding.Ultimately, the model did best when predicting the number ofspectators based on the Facebook activity during a match as wellas the activity from the last two weeks leading up to the match.Furthermore, the data reveals that photos generates the mostactivity on the national team’s page and with videos runningat higher production costs there might be some unexploitedpotential for DBU to improve its social media marketing strategy.Although data limitations are present, this research concludesthat predictive models based on big social data can indeed offerimportant insights for companies to understand their customerbase and how to improve marketing strategies.Index Terms—Big data, Big social media data, Danish NationalTeam, DBU, Facebook data, Football fans, Spectators, TV rating