Identifying vulgar content in eMule network through text classification

Through years of development, the cyberspace has been dominated by traffic of peer-to-peer (P2P) file sharing applications. Among them, eMule is especially favored by millions of P2P users all over the world. However, it is very difficult to manage the content which is delivered through eMule due to its distributed property, thus a large number of vulgar content (e.g., pornographic and violent files) is existing in eMule. Since children and adolescents are the main force of eMule users, it is quite necessary to provide an efficient method to identify and filter the vulgar content for the sake of innocent children and adolescents. In this study, an automatic framework based on text classification is proposed to identify and filter vulgar content in eMule. Filename is used as the feature to carry out the elementary research on the effectiveness of our framework, although filename may be changed freely by eMule users. We aim to achieve high accuracy when identifying and filtering vulgar content, thus to raise the quality of the content delivered in eMule to a higher level.