Abstract:
The largest shared
information source, the
World Wide Web has
been increasing a
tremendous proliferation
in the amount of
information rapidly. As a
result of its huge sharing
and highly dynamic
data, there is a need for
grouping the documents
into clusters for faster
information retrieval.
Clustering web
documents is collection
of documents into groups
such that the documents
within each group are
similar to each other.
Document clustering is
one of the main
challenging tasks in web
data mining and it is still
requires an efficient
clustering techniques.
The typical way of
representing a web
document is a huge box
of terms. The
representation of these
terms is often
unsatisfactory as it does
not exploit the
semantics. This paper
proposes Particle swarm
Optimization (PSO) and
Ontology for clustering
of text documents. A
domain Ontology is
developed thus it
enriched with semantic
and synonyms for the
representation of terms.
Particle Swarm
Optimization (PSO)
algorithm is used to
cluster high voluminous
of data efficiently. This
paper presents
comparative results of
using PSO algorithm
only and PSO algorithm
using Ontology for
clustering web
documents. The analysis
result of test data is
efficient enough in
representation of terms by using Ontology and
the performance of PSO
clustering algorithm is
high in intra cluster and
inters cluster similarity.
