Community-Based Scholar Recommendation Modeling in Academic Social Network Sites

Academic social network sites (ASNSs) have experienced rapid growth in recent years. Large amounts of users hope to make friends with other users for potential academic collaborations in ASNSs. Though there are many scholar recommendation systems, they mainly consider the content similarity of users’ profiles. In fact, the communities of ASNSs can offer rich networking information to make recommendations. In this paper, we propose a community-based scholar recommendation model in ASNSs. We firstly construct research-fields-based graphs, detect communities in the graphs by Louvain method and then make scholar recommendation by calculating friendship scores. We also implement the model on a real world dataset from an academic social network site called SCHOLAT. And the experimental results demonstrate that our approach improves the recommendations of core network members and outperforms the content-based user recommendation method.

[1]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[2]  M E J Newman,et al.  Community structure in social and biological networks , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[3]  M. Newman,et al.  Finding community structure in very large networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  Tamara Heck,et al.  Combining social information for academic networking , 2013, CSCW.

[5]  Byron L. D. Bezerra,et al.  A symbolic approach for content-based information filtering , 2004, Inf. Process. Lett..

[6]  Flavius Frasincar,et al.  Advances in Conceptual Modeling - Applications and Challenges, ER 2010 Workshops ACM-L, CMLSA, CMS, DE@ER, FP-UML, SeCoGIS, WISM, Vancouver, BC, Canada, November 1-4, 2010. Proceedings , 2010, ER Workshops.

[7]  Liu Ji.  Aggregating collaborative recommendation method based on network cloud community , 2011 .

[8]  Yang Shen,et al.  Emotion mining research on micro-blog , 2009, 2009 1st IEEE Symposium on Web Society.

[9]  Yuan Zhao,et al.  The similar scholar recommendation in Schol@t , 2012, Proceedings of the 2012 IEEE 16th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[10]  Loriene Roy,et al.  Content-based book recommending using learning for text categorization , 1999, DL '00.

[11]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[13]  Giseli Rabello Lopes,et al.  Collaboration Recommendation on Academic Social Networks , 2010, ER Workshops.

[14]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[15]  Antonino Nocera,et al.  An approach to providing a user of a "social folksonomy" with recommendations of similar users and potentially interesting resources , 2011, Knowl. Based Syst..

[16]  Yong Tang,et al.  Semantic description of scholar-oriented social network cloud , 2010, The Journal of Supercomputing.

[17]  Jianguo Li,et al.  The implementation of an online information service model based on academic social network systems , 2012, 2012 8th International Conference on Information Science and Digital Content Technology (ICIDT2012).