Matchballs – A Multi-Agent-System for Ontology-Based Collaborative Learning Games

Abstract

Computer games are currently one of the computer science applications with the highest amount of users. The "serious gaming" approach tries to use the attraction (i.e. the fun factor) of such media not only for entertainment purposes, but also to convey serious content at the same time. Serious games have been established in vocational and advanced training over the last years and have a big potential for informal further vocational training. This paper presents a multi-agent-architecture for collaborative, serious and casual games. The focus is on casual games, since these are known to be small games with a high potential for frequent gaming by people of various social and educational background. To be flexible concerning the learning domain an ontology-based approach has been used. The ontology may easily be exchanged to adapt the game to another domain. Furthermore, the data created in the games can be used in a "wisdom of the crowd" approach to enhance the ontology. To test our architecture, an ontology on food safety and hazardous material regulations was created and the game was evaluated with a group of technician students of a professional training academy.