Formal Procedural Content Generation in games driven by social analyses

Millions of people play online computer games every day. Massive Multiplay Online (MMO) Games suffer a great problem: Developing new content for games (especially for Role Play Games-RPG) is an highly expensive and time consuming task. On the other hand, Players usually complain of static and repetitive contents of games and a rapid decrease of their interest in the games is evident after main patches deployment. In this scenario, a way to create new dynamic game contents is appealing, in particular if it depends on players needs and expectations. In this paper we describe a framework and a methodology for Procedural Content Generation (PCG) of game contents. The methodology exploit formal Multi-Agent based models and planning techniques.