Abstract : The broadcasting communication mode is widely used in Vehicular Ad~hoc Networks (VANETs). It is used for sending emergency messages, road-traffic information or to help routing protocols to determine routes. This communication mode is known to be hard to achieve efficiently since it depends on the network density. Indeed, broadcasting methods may cause network congestion if they are not well designed. This paper introduces a novel Autonomic Dissemination Method (ADM) which delivers messages in accordance with given message classes and network density levels. The proposed approach is based on two steps: an offline optimization process and an online adaptation to the network characteristics. ADM allows each node to dynamically adapt its broadcasting strategy not only with respect to the network density, but also according to the class of the message to send: emergency (high-priority), road-traffic (medium-priority) or either comfort message (low-priority). The ultimate goal of ADM is to make effective use of radio resources when there are many messages to send simultaneously. This approach increases the efficiency of the broadcast process in terms of message delivery ratio, latency and interferences reduction. The autonomic computing paradigm improves the robustness of protocols.