Automated Classification Software – What
is it?
The complexities of
storing and retrieving information in today’s information
environment, has led the emergence of a range of software
applications designed to improve organisation and access to
content within websites. One application that is increasingly
being used by website creators is known as Automated
Classification software which is designed to automatically
categorise electronic content using index terms and metadata
then organise the content to suit the needs requirements of
organisation/site owners. Within this process, human
intellectual processes are replaced by machine automated
classification to categorise content (Golub, 2005). As well as
providing an effective solution to managing large volumes of
content, this type of software provides considerable cost
benefits to the company/site owners by reducing the
time and effort needed to organise, channel and distribute
information. Generally
speaking, software can be individually configured to arrange
content by categories such as shared meaning, co-location, linking and sequencing (Batley, 2005). The term Automated
classification is also known as Automated Indexing and Content
Classification.
How can Automated Classification
help with a sites design and
organisation?
·
Organising documents into subject
categories for topical browsing
·
Grouping search
results
·
Personalised routing of
information
·
Filtering of unwanted
content
(Sebastini, 2002; Jain et al., 1999, cited by Golub,
2005)
An additional benefit to applications that
use metadata and tagging is that companies/ site owners are in
a better position to address the rights management, ownership
and authenticity of the content they provide access to.
Metadata can contain information about ownership and
intellectual property rights – of particular importance in the
digital environment where information can be accessed and
reproduced (Batley, 2007).
For an
evaluation of one Automated Software application please refer
to our Product Review
Recommind Decisiv .
References;
Batley, S. (2007). Information
Architecture for information professionals.
Chandos: Oxford.
Golub, K. (2005). Automated subject
classification of textual web documents. Journal of
Documentation, 62(3). 350-371. Emerald
Publishing.
Morville, P. & Rosenfeld, L., (2007). Information
architecture for the world wide web, 3rd
edn, O’Reilly,
Beijing. |