Knowledge Extraction from Games (KEG) is a workshop exploring questions of and approaches to the automated extraction of knowledge from games. We use “knowledge” in the broadest possible sense, including but not limited to design patterns, game rules, character graphics, environment maps, music and sound efects, high-level goals or heuristic strategies, transferable skills, aesthetic standards and conventions, or abstracted models of games. This year we had 13 submissions! 11 of which were accepted for publication and presentation. In addition to the accepted talks, we also had 2 invited talks: 1) from Alexander Zook on the topic of player behavior and automatic playtesting, and 2) from Srijan Kumar on the topic of extracting and analyzing networks of discussion interactions. We would also like to thank and acknowledge our program committee without whom none of this would be possible!