License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-17910
URL: http://drops.dagstuhl.de/opus/volltexte/2008/1791/
Go to the corresponding Portal


Passant, Alexandre ; Mulvany, Ian ; Mika, Peter ; Maisonneuve, Nicolas ; Löser, Alexander ; Cattuto, Ciro ; Bizer, Christian ; Bauckhage, Christian ; Alani, Harith

08391 Group Summary -- Mining for Social Serendipity

pdf-format:
Document 1.pdf (252 KB)


Abstract

A common social problem at an event in which people do not personally know all of the other participants is the natural tendency for cliques to form and for discussions to mainly happen between people who already know each other. This limits the possibility for people to make interesting new acquaintances and acts as a retarding force in the creation of new links in the social web. Encouraging users to socialize with people they don't know by revealing to them hidden surprising links could help to improve the diversity of interactions at an event. The goal of this paper is to propose a method for detecting extit{"surprising"} relationships between people attending an event. By extit{"surprising"} relationship we mean those relationships that are not known a-priori, and that imply shared information not directly related with the local context of the event (location, interests, contacts) at which the meeting takes place. To demonstrate and test our concept we used the Flickr community. We focused on a community of users associated with a social event (a computer science conference) and represented in Flickr by means of a photo pool devoted to the event. We use Flickr metadata (tags) to mine for user similarity not related to the context of the event, as represented in the corresponding Flickr group. For example, we look for two group members who have been in the same highly specific place (identified by means of geo-tagged photos), but are not friends of each other and share no other common interests or, social neighborhood.

BibTeX - Entry

@InProceedings{passant_et_al:DSP:2008:1791,
  author =	{Alexandre Passant and Ian Mulvany and Peter Mika and Nicolas Maisonneuve and Alexander L{\"o}ser and Ciro Cattuto and Christian Bizer and Christian Bauckhage and Harith Alani},
  title =	{08391 Group Summary -- Mining for Social Serendipity},
  booktitle =	{Social Web Communities },
  year =	{2008},
  editor =	{Harith Alani and Steffen Staab and Gerd Stumme},
  number =	{08391},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2008/1791},
  annote =	{Keywords: Serendipity, online activity, context, ubiquitous computing}
}

Keywords: Serendipity, online activity, context, ubiquitous computing
Seminar: 08391 - Social Web Communities
Issue Date: 2008
Date of publication: 22.12.2008


DROPS-Home | Fulltext Search | Imprint Published by LZI