Fast Recommendation on Bibliographic Networks
ASONAM '12 Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012)
Diversified recommendation on graphs: pitfalls, measures, and algorithms
Proceedings of the 22nd international conference on World Wide Web
Hi-index | 0.00 |
The academic community has published millions of research papers to date, and the number of new papers has been increasing with time. To discover new research, researchers typically rely on manual methods such as keyword-based search, reading proceedings of conferences, browsing publication lists of known experts, or checking the references of the papers they are interested. Existing tools for the literature search are suitable for a first-level bibliographic search. However, they do not allow complex second-level searches. In this paper, we present a web service called TheAdvisor (http://theadvisor.osu.edu) which helps the users to build a strong bibliography by extending the document set obtained after a first-level search. The service makes use of the citation graph for recommendation. It also features diversification, relevance feedback, graphical visualization, venue and reviewer recommendation. In this work, we explain the design criteria and rationale we employed to make the TheAdvisor a useful and scalable web service along with a thorough experimental evaluation.