TY - GEN
T1 - Social patterns
T2 - 2013 IEEE 2nd International Network Science Workshop, NSW 2013
AU - Leung, Alice
AU - Dron, William
AU - Hancock, John P.
AU - Aguirre, Matthew
AU - Purnell, Jon
AU - Han, Jiawei
AU - Wang, Chi
AU - Srivastava, Jaideep
AU - Mahapatra, Amogh
AU - Roy, Atanu
AU - Scott, Lisa
PY - 2013
Y1 - 2013
N2 - A set of behavior rules, personal characteristics, group affiliations and roles was used to generate a dataset of mixed communication actions modeling those at a large organization. Several different approaches to community detection and modeling were applied to this generated dataset, in order to compare the strengths and range of applicability of different algorithms. Graph partitioning methods performed well at assigning membership to formal, exclusive groups such as organizational departments, if there is a priori knowledge of the target number of groups. SSDE-cluster, a fast and scalable algorithm, performed well in detecting normal departments and can be used when the number of groups is not known. It also was able to detect small overlapping groups, but with only moderate accuracy. Clique enumeration performed well in detecting small overlapping groups, when a priori knowledge of average group size was used. Different methods of constructing social network graphs from the mixed communication actions were investigated, as well as different link weighing methods. We conclude that behavior-generated datasets with complex and complete ground truths are useful for collaborative validation of different community and role detection and modeling methods.
AB - A set of behavior rules, personal characteristics, group affiliations and roles was used to generate a dataset of mixed communication actions modeling those at a large organization. Several different approaches to community detection and modeling were applied to this generated dataset, in order to compare the strengths and range of applicability of different algorithms. Graph partitioning methods performed well at assigning membership to formal, exclusive groups such as organizational departments, if there is a priori knowledge of the target number of groups. SSDE-cluster, a fast and scalable algorithm, performed well in detecting normal departments and can be used when the number of groups is not known. It also was able to detect small overlapping groups, but with only moderate accuracy. Clique enumeration performed well in detecting small overlapping groups, when a priori knowledge of average group size was used. Different methods of constructing social network graphs from the mixed communication actions were investigated, as well as different link weighing methods. We conclude that behavior-generated datasets with complex and complete ground truths are useful for collaborative validation of different community and role detection and modeling methods.
KW - clustering
KW - communication models
KW - community detection
KW - generated datasets
KW - group detection
KW - rule-based behaviors
UR - http://www.scopus.com/inward/record.url?scp=84886067103&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84886067103&partnerID=8YFLogxK
U2 - 10.1109/NSW.2013.6609198
DO - 10.1109/NSW.2013.6609198
M3 - Conference contribution
AN - SCOPUS:84886067103
SN - 9781479904365
T3 - Proceedings of the 2013 IEEE 2nd International Network Science Workshop, NSW 2013
SP - 82
EP - 89
BT - Proceedings of the 2013 IEEE 2nd International Network Science Workshop, NSW 2013
Y2 - 29 April 2013 through 1 May 2013
ER -