Article Preview
Top1. Introduction
Searching the Web has become more challenging due to the rapid growth in information. The query response time and the scalability issue in the information retrieval can be reduced by cluster retrieval approach. Clustering of retrieved result is used to present more organized result to the user. Clustering simplifies web search engine work by grouping large amount of documents, retrieved according to a given query (Madyloval & Öğüdücü, 2009). Generally, text document clustering methods attempt to group the document based on some topic that is different than those topics represented by the other groups (Frakes & Yates, 1992). For the document clustering, the current keyword-based methodologies tend to be inconsistent and ineffective when the terms are used for cluster analysis. Most of document clustering algorithms use Vector Space Model (VSM) for document representation (Salton, 1989). The vector space model is a widely used data representation for document classification and clustering (Salton & McGill, 1983; Salton, Wong, & Yang, 1975). VSM represents documents as vectors in the space in terms, and measures using inner-products. VSM ignores semantic relations between terms. The research problem of improving relevance in search and ranking of document can be done by considering the semantics of relations. Using ontology as background knowledge can improve document clustering quality with its concept hierarchy knowledge (Zhang et al., 2008).
Ontology based information retrieval matches the relevance of a user generated query against an ontology-based knowledge-base. The ontological information retrieval utilizes the relations between the keywords (Castells, Fernandez, & Vallet, 2007). The vector space model can be combined with the ontology based information retrieval to retrieve the relevant documents (Vallet, Fernande, & Castells, 2005). The efficiency of the information retrieval process can be increased by annotating documents with semantic information.
The motivation of our research is that the terms in the document have multiple meanings. Thus, providing ontology based similarity certainly helps to formulate more effective clustering according to the user’s needs. The objective of the research is to define a model for the ontology based annotation and clustering using particle swarm optimization. In this paper we have defined how to apply ontology based annotation method to improve the clustering of the documents. The quality of the solution obtained can be improved by using annotated weights and optimized clustering algorithm.
The idea of the approach is based on concepts and relations extracted from the documents. Our approach consists of three major steps. First, the concepts and their relations are extracted from the document based on ontology based annotation. Second, ontology based indexing is done on the corpus. Third, the PSO-based clustering algorithm finds the optimized clusters.
The main contributions of this paper are:
- 1.
Most of the document clustering approaches do not consider the semantic similarity of terms.
- 2.
We propose a PSO based clustering method on the document represented based on semantic similarity.
- 3.
We conduct experiments to evaluate the ontology based method and the traditional vector space model. The results show that the ontology based model yields better precision and recall.
In the following section, related literature from the field of ontology based methodologies and clustering using particle swarm algorithm is surveyed. Section 3, describes the proposed methodology that includes the document annotation, similarity measure and clustering framework. Section 4 presents the system architecture that implements the ontology based model for document clustering. Section 5 describes the data sets and experimental results. Section 6 presents the conclusion and future work.