14.1399, Software: Leximancer: Text and/or Content Analysis

[LINGUIST List]

LINGUIST List:  Vol-14-1399. Thu May 15 2003. ISSN: 1068-4875.

Subject: 14.1399, Software: Leximancer: Text and/or Content Analysis

Moderators: Anthony Aristar, Wayne State U.<aristar at linguistlist.org>
            Helen Dry, Eastern Michigan U. <hdry at linguistlist.org>

Reviews (reviews at linguistlist.org):
	Simin Karimi, U. of Arizona
	Terence Langendoen, U. of Arizona

Home Page:  http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, Wayne
State University, and donations from subscribers and publishers.

Editor for this issue: Karen Milligan <karen at linguistlist.org>
 ==========================================================================
To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.html.
=================================Directory=================================

1)
Date:  Mon, 12 May 2003 14:11:30 +1000
From:  Peter Hollands <p.hollands at humanfactors.uq.edu.au>
Subject:  Leximancer

-------------------------------- Message 1 -------------------------------

Date:  Mon, 12 May 2003 14:11:30 +1000
From:  Peter Hollands <p.hollands at humanfactors.uq.edu.au>
Subject:  Leximancer


Having an interest in linguistics you will no doubt have some interest
in the analysis of text and/or content-analysis.  A software tool has
been developed at the University of Queensland in Australia that makes
such analysis a whole lot easier.

Leximancer is a software tool capable of objectively analysing the
content of text simply, quickly and effectively. Unlike other systems,
Leximancer requires no hand-coding and performs its analysis
completely automatically by extracting the semantic networks contained
within the document set, otherwise known as unsupervised ontology
discovery.

Leximancer also differs by not relying on parsing as its analytical
base, using instead mathematical and scientific calculations based on
the Bayesian approach to prediction. Such an approach has produced a
system capable of working just as effectively in any of the European
languages.

Any number of different lines of enquiry may be followed depending on
the needs of the user. Those interested in mapping or classifying
documents with customised concepts may use hand-coding to configure
the analysis any way they choose, providing an extraordinary level of
customisation.

Leximancer succeeds by recognising the major issues or concepts within
the text and represents them both on an interactive map as well as in
tabular form. This map allows the analysts or researcher to explore
the background data on which each relationship is based.  Each concept
is positioned in such a way as to graphically highlight its
relationship with each and every other concept, such juxtapositions
even permitting the discovery of relationships that may otherwise
remain hidden.

To achieve this level of analysis, several novel algorithms were
developed including a learning optimiser for automatically selecting,
learning and adapting a concept from the word usage within the text,
and an asymmetric scaling process for generating a cluster map of
concepts based on co-occurrence in the text.

Leximancer is now in use in universities throughout Australia, with a
number of State government departments and with clients in the UK, the
USA and Italy.

Contact details:

The product was developed at the:
The Key Centre for Human Factors and Applied Cognitive Psychology
The University of Queensland
St Lucia
Brisbane
Qld 4172

Leximancer is offered through:
Uniquest Pty Ltd
Research Road
The University of Queensland
St Lucia
Qld 4172

Ph: 3365 7196

http://www.leximancer.com/


Peter Hollands
Consulting & Industry Liaison Manager
The Key Centre for Human Factors & Applied Cognitive Psychology at the
University of Queensland
07 3365 7196

---------------------------------------------------------------------------
LINGUIST List: Vol-14-1399