Citation retrieval in digital libraries

Abstract

Currently more and more research papers are being published in the form of digital libraries on the web. How to search them efficiently and effectively is a big challenge for researchers. With a static subject tree index the paper and with the traditional query mechanism, many problems appear. The detail-level topics can hardly be found, the emerging new area can not be identified, the non-semantically related papers can hardly be retrieved, and the key papers in the area can not be obviously pointed out. In order to solve these problems, this paper proposes a novel approach to map the citation retrieval problem into a graph-partitioning problem. All citations in a digital library will be mapped to a citation graph through their reference links. It is observed that the citation graph is not evenly connected. Highly connected sub-graphs will often emerge. Different sub-graph will represent different topic and to partition the graph to higher levels can reveal the detail topics. The different connectivity can also help to find the hot topics, related topics and key citations. Since all these can be done automatically and efficiently, the user's manual effort to search citations will be saved but the results will be more comprehensive and accurate.