A multiple-perspective approach to constructing and aggregating Citation Semantic Link Network

Various kinds of semantic relationships exist among scientific literatures which worth to be explored. This paper proposes a Citation Semantic Link Network (C-SLN) to describe the semantic information over the literature citation networks. A framework of the construction of C-SLN is represented by integrating several NLP methods. The methods of aggregating a C-SLN and the algorithms of discovering opinion communities in a C-SLN are also discussed. Based on a multi-perspective exploration on the C-SLN, we can effectively find articles of high importance, aggregate the function of citations and detect opinion communities among scientific documents.