Analyzing the Strength of Co-authorship Ties with Neighborhood Overlap

Evaluating researchers' scientific productivity usually relies on bibliometry only, which may not be always fair. Here, we take a step forward on analyzing such data by exploring the strength of co-authorship ties in social networks. Specifically, we build co-authorship social networks by extracting the datasets of three research areas sociology, medicine and computer science from a real digital library and analyze how topological properties relate to the strength of ties. Our results show that different topological properties explain variations in the strength of co-authorship ties, depending on the research area. Also, we show that neighborhood overlap can be applied to scientific productivity evaluation and analysis beyond bibliometry.

[1]  Kåre Synnes,et al.  The strength of social strength: an evaluation study of algorithmic versus user-defined ranking , 2014, SAC.

[2]  Raj Jain,et al.  The art of computer systems performance analysis - techniques for experimental design, measurement, simulation, and modeling , 1991, Wiley professional computing.

[3]  Mark S. Granovetter.  The Strength of Weak Ties , 1973, American Journal of Sociology.

[4]  Ana Paula Couto da Silva,et al.  Community-based endogamy as an influence indicator , 2014, IEEE/ACM Joint Conference on Digital Libraries.

[5]  D. Pendlebury.  The use and misuse of journal metrics and other citation indicators , 2009, Archivum Immunologiae et Therapiae Experimentalis.

[6]  Mao Lin Huang,et al.  Analysis and Visualization of Co-authorship Networks for Understanding Academic Collaboration and Knowledge Domain of Individual Researchers , 2006, International Conference on Computer Graphics, Imaging and Visualisation (CGIV'06).

[7]  Shuguang Guan,et al.  Efficient algorithm based on neighborhood overlap for community identification in complex networks , 2012 .

[8]  Rodrygo L. T. Santos,et al.  Aggregating productivity indices for ranking researchers across multiple areas , 2013, JCDL '13.

[9]  The Work Habits of Eminent Scholars , 1974 .

[10]  M. Newman,et al.  The structure of scientific collaboration networks. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Alexander Weber,et al.  Analysing Social Networks Within Bibliographical Data , 2006, DEXA.

[12]  Mohammed J. Zaki.  Data Mining and Analysis: Fundamental Concepts and Algorithms , 2014 .

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

[14]  José María Cavero Barca,et al.  Computer science research: more production, less productivity , 2013, Scientometrics.

[15]  Francisco J. Acedo,et al.  Co-Authorship in Management and Organizational Studies: An Empirical and Network Analysis , 2006 .

[16]  A. Barabasi,et al.  Evolution of the social network of scientific collaborations , 2001, cond-mat/0104162.

[17]  Baowen Xu,et al.  A Unified Semi-supervised Framework for Author Disambiguation in Academic Social Network , 2014, DEXA.

[18]  W. Glänzel,et al.  Analysing Scientific Networks Through Co-Authorship , 2004 .

[19]  Yan Zhang,et al.  To better stand on the shoulder of giants , 2012, JCDL '12.

[20]  Giseli Rabello Lopes,et al.  Using link semantics to recommend collaborations in academic social networks , 2013, WWW.

[21]  E. David,et al.  Networks, Crowds, and Markets: Reasoning about a Highly Connected World , 2010 .

[22]  Bhavana Dalvi,et al.  Structure, tie persistence and event detection in large phone and SMS networks , 2010, MLG '10.

[23]  Flavio Figueiredo,et al.  Characterizing scholar popularity: A case study in the Computer Science research community , 2014, IEEE/ACM Joint Conference on Digital Libraries.

[24]  R. Burt.  Structural Holes and Good Ideas1 , 2004, American Journal of Sociology.

[25]  Mohamed A. Sharaf,et al.  Databases Theory and Applications , 2014, Lecture Notes in Computer Science.