Social Event Detection via sparse multi-modal feature selection and incremental density based clustering


Samangooei, Sina, Hare, Jonathon, Dupplaw, David, Niranjan, Mahesan, Gibbins, Nicholas, Lewis, Paul H., Davies, Jamie, Jain, Neha and Preston, John (2013) Social Event Detection via sparse multi-modal feature selection and incremental density based clustering At MediaEval 2013 / Social Event Detection for Social Multimedia, Spain.

Download

[img] PDF sed.pdf - Version of Record
Download (107kB)
[img] PDF Mediaeval-Search.pdf - Other
Download (2MB)
[img] PDF sed2013-long.pdf - Other
Download (3MB)
[img] PDF sed2013-short.pdf - Other
Download (4MB)

Description/Abstract

Combining items from social media streams, such as Flickr photos and Twitter tweets, into meaningful groups can help users contextu- alise and effectively consume the torrents of information now made available on the social web. This task is made challenging due to the scale of the streams and the inherently multimodal nature of the information to be contextualised. We present a methodology which approaches social event detection as a multi-modal clustering task. We address the various challenges of this task: the selection of the features used to compare items to one another; the construction of a single sparse affinity matrix; combining the features; relative importance of features; and clustering techniques which produce meaningful item groups whilst scaling to cluster large numbers of items. In our best tested configuration we achieve an F1 score of 0.94, showing that a good compromise between precision and recall of clusters can be achieved using our technique.

Item Type: Conference or Workshop Item (Paper)
Venue - Dates: MediaEval 2013 / Social Event Detection for Social Multimedia, Spain, 2013-10-18
Organisations: Web & Internet Science
ePrint ID: 358837
Date :
Date Event
18 October 2013Accepted/In Press
Date Deposited: 11 Oct 2013 17:09
Last Modified: 17 Apr 2017 14:47
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/358837

Actions (login required)

View Item View Item