Advertising Strategies: Learning Competence through Cooperative Game Playing

In this paper we consider the competition on the Internet between information providers to maximise their exposure to a relevant audience. Spammers and Search engine gamers adopt a selfish, noncooperative strategy where the goal is to bring the target site or product to the attention of as many people as possible, regardless of the consequences. In contrast, we describe a co-operative strategy where agents engage in ‘language games’ in order to learn and index the distributed topic competence of other agents. By participating in the game strategies, agents have a two-fold reward: their local topic competence is advertised to a relevant distributed audience and their own problem-solving capabilities are enhanced by allowing them to draw upon the competences of other agents. We describe how we are using this technique to produce a topic-centric view of the blogosphere and we discuss work we intend to pursue to improve the strategies available to our agents.

• Type: Conference
• Year: 2005
• Where: ICCBR
• Authors: Paolo Avesani, Conor Hayes
• Keywords: ICCBR 2005, Relevant Distributed Audience, Search Engine Gamers, Topic Competence