TheAdvisor: a webservice for academic recommendation

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.

[1]  Ümit V. Çatalyürek,et al.  Direction Awareness in Citation Recommendation , 2012 .

[2]  Ümit V. Çatalyürek,et al.  Diversifying Citation Recommendations , 2012, ACM Trans. Intell. Syst. Technol..

[3]  Ümit V. Çatalyürek,et al.  Towards a personalized, scalable, and exploratory academic recommendation service , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[4]  Ümit V. Çatalyürek,et al.  Diversified recommendation on graphs: pitfalls, measures, and algorithms , 2013, WWW.

[5]  Ümit V. Çatalyürek,et al.  Result Diversification in Automatic Citation Recommendation , 2013 .

[6]  Ümit V. Çatalyürek,et al.  Fast Recommendation on Bibliographic Networks , 2012, 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.

[7]  Ümit V. Çatalyürek,et al.  Fast recommendation on bibliographic networks with sparse-matrix ordering and partitioning , 2012, Social Network Analysis and Mining.