OSNI: Searching for Needles in a Haystack of Social Network Data

This paper presents the Online Social Network Investigator (OSNI), a scalable distributed system to search social network data, based on a spatiotemporal window and a list of keywords. Given that only 2% of tweets are geolocated, we have implemented and compared various state-of-art location estimation techniques. Further, to enrich the context of posts, associations of images to terms are estimated through various classification techniques. The accuracies of these estimations are evaluated on large real datasets. OSNI’s query interface is available on the Web.

• Type: Journal
• Year: 2016
• Where: EDBT
• Authors: Shiwen Cheng, James Fang, Vagelis Hristidis, Harsha V. Madhyastha, Niluthpol Chowdhury Mithun, Dorian Perkins, Amit K. Roy-Chowdhury, Moloud Shahbazi, Vassilis J. Tsotras
• Keywords: Database, EDBT 2016