Recently, discovering aggressive communities has become an increasingly critical task. Many conclusion have been expected, most of which only use correlation structure. However, rich information is cipher in the content of social chain such as node content and edge contented, which is fundamental to discover topically meaningful association. Therefore, to disclose both structurally and topically meaningful association, linkage architecture, node comfortable and edge content should be unified. The main objection lies in how to integrate those dynamics in a seamless way. This paper nominates a novel transformation of comfortable based network into a Node-Edge Interaction chain where linkage architecture, node content and boundary comfortable are fixed seamlessly. A differential action based access is expected to incrementally continue the Node Edge Interactional chain as the comfortable based network derives. To capture the semantic aftermath of different edge types, a transition chance matrix is construct for the NEI network. Based on this, heterogeneous accidental walk is enforced to discover aggressive communities, leading to a new dynamic association detection method describe Node Edge Interaction Walk (random Walk).