As we did 4 years ago
, it's the time to make a network analysis of the Euro 2008 soccer tournament. Fortunately, full passes and intercepts statistics are being published
; unfortunately, it's not done per match; it will not be difficult to extract per match stats via differential analysis, I guess. For the time being, I have created a a git repo with code that scrapes the page and downloads and distills player-per-player pass stats
; more stuff will have to be done: put in in a format that can be understood by some network analysis program, and do the actual stats.
Our target is to try and find which network measure is a good predictor for match outcome, and, eventually, to predict which team will be the winner based on that. And publish it eventually in some congress or journal, obviously.
If you want to commit code to the repo, please sign in GitHub and send me your ID. Good luck!
Tags: soccer, social network analysis, euro 2008