A fuzzy approach to the conceptual identification of ememes on the blogosphere

The paper addresses the problem of e-memes (electronic memes) representation and identification in the blogosphere, and it aims at defining the basis of a new conceptual model. First, an ememe is formally defined as a conceptual information granule by means of an OWL schema; then a process is proposed to retrieve from the blogosphere the posts dealing with the ememe. The proposed process extracts from the formal definition of the ememe some keyword-based queries that are submitted to a search engine to retrieve posts that are potentially related to the ememe. The post contents are then filtered by evaluating their fidelity to the ememe conceptual definition by applying a lexicographic analysis and part of speech tagging. Ordered Weighted Averaging (OWA) operators are used to this purpose. Measures of mutation, spread, and longevity of an ememe are also proposed.