Information Technology Reference
In-Depth Information
Fig. 5.1 Tripartite graph
structure of a tagging system.
An edge linking a user, a tag
and a resource (website)
represents one tagging
instance
However, we are more interested in the tags applied to individual URIs. An
early line of research that has attempted to formalize and quantify the underlying
dynamics of collaborative tagging systems is Golder and Huberman (2006), which
also make use of del.ici.ous data. They show the majority of sites reach their peak
popularity, the highest frequency of tagging in a given time period, within 10 days of
being saved on del.icio.us (67% in their data set), though some sites are rediscovered
by users (about 17% in their data set), suggesting stability in most sites but some
degree of 'burstiness' in the dynamics that could lead to cyclical patterns of stability
characteristic of chaotic systems. Importantly, Golder and Huberman find that the
distribution of tags within a given site stabilizes over time, usually around 100
tagging events. They do not, however, examine what type of distribution arises
from a stabilized tagging process, nor do they present a method for determining the
stability of the distribution which we see as central to understanding the possible
utility of tagging systems. Thus, the first task should be to determine the stability of
tagging systems.
5.1.2
The Tripartite Structure of Tagging
To begin, we review the conceptual model of generic collaborative tagging systems
theorized in order to make predictions about collaborative tagging systems based on
empirical data and based on generative features of the model (Mika 2005).
There are three main types of entities that compose any tagging system:
￿
The users of the system (people who actually do the tagging)
￿
The tags themselves
￿
The resources being tagged (in this case, the websites)
Each of these can be seen as forming separate spaces consisting of sets of nodes,
which are linked together by edges (see Fig. 5.1 ). The first space, the user space ,
consists of the set of all users of the tagging system , where each node is a user.
The second space is the tag space , the set of all tags , where a tag corresponds to
Search WWH ::




Custom Search