LiterMiner: An Academic Literature Mining System

This paper addresses several key issues in the LiterMiner system, which aims at extracting and mining academic social networks. Specifically, the system focuses on: (1) Integrating the publication data into the academic network from existing article records; (2) Detecting and visualizing communities and evolution in the network; and (3) Analyzing the network multi-dimensionally. We provide a preprocessing framework to deal with the name ambiguity problem in data integration. Furthermore, we provide multiple algorithms to detect communities, and visualize both the communities and the evolution of networks with user friendly interface. Besides, multi-dimensional analyses of related networks have been provided based on the implementation and extension of the GraphOLAP framework. In this paper, we describe the architecture and main features of the system. We also present a case study with real data sets to show these features.