Exploring topical and social groups

Groups play a crucial role in social networks. To name just a few: we find emotional support among our family members and groups of friends, we work in specialized teams, and we seek advices in expert communities. Hence, it is crucial to understand whether there are different types of groups and how they differ. In sociology, the common identity and common bond theories help to explain the origins and characteristics of topical and social groups. Based on this theory we proposed a classifier that distinguishes between topical and social groups in OSNs. Furthermore, we have also proposed a novel method for detection of topical groups in the Twitter social network, that identifies groups of users who are experts on or interested in a common topic. We found that Twitter consists of topical groups related to not only popular topics of general interest such as politics, music and sports, but also highly specialized topics ranging from geology, neurology, to astrophysics and karate.



Deep Twitter Diving: Exploring Topical Groups in Microblogs at Scale
Parantapa Bhattacharya, Saptarshi Ghosh, Juhi Kulshrestha, Mainack Mondal, Muhammad Bilal Zafar, Niloy Ganguly, and Krishna P. Gummadi. ACM Conference on Computer Supported Cooperative Work and Social Computing (CSCW), Baltimore, USA, February 2014.

Distinguishing topical and social groups based on common identity and bond theory
Przemyslaw A. Grabowicz, Luca Maria Aiello, Victor M. Eguiluz, Alejandro Jaimes. Proceedings of the sixth ACM international conference on Web search and data mining (WSDM), Rome, Italy, February 2013.




Saptarshi Ghosh is awarded a Humboldt Postdoctoral Research Fellowship
July 2014

Mainack Mondal, Bimal Viswanath and Krishna Gummadi, along with their co-authors win SOUPS distinguished paper award
July 2014

Juhi Kulshrestha receives Google Anita Borg Scholarship
May 2013

Cristian Danescu-Niculescu-Mizil wins WWW best paper award
May 2013