An Ontology-based and Domain Specific Clustering Methodology for Financial Documents

Financial documents play an important role in modern financial analysis and information retrieval tasks. In order to accomplish various investigational needs, financial organizations continuously search for accurate and meaningful unsupervised document classification techniques. Nevertheless, unsupervised document categorization or document clustering is a challenging problem studied by many scientists. Incorporating semantic knowledge from an ontology into document clustering has been extensively studied and it has provided enhanced clustering performances. The incorporated semantic knowledge is generally used for identifying the correct meanings of the ambiguous words in the documents. Most of the proposed methodologies were experimented on general document datasets and most of the few available domain specific clustering studies were constrained to specific domains where complete domain ontologies are available. Although financial domain has several domain ontologies, none of them are complete and suitable for semantic document clustering. In this context, our study proposes a document clustering methodology for financial documents which adapts WordNet ontology to the financial domain to serve as an external knowledge source. This study empirically shows that nouns are relatively prevalent and more important for document clustering rather than other terms in a document. Afterwards, a subset of nouns is identified as most important for the clustering, based on their frequency distribution within the main noun list. We developed a word sense disambiguation technique which uses ontological knowledge for noun disambiguation. Finally, nouns in each document are disambiguated with the proposed word sense disambiguation technique, associated with tf-idf weights and clustered. On the basis of the empirical results of this research, it can be concluded that the proposed methodology can significantly enhance the clustering performance compared to no disambiguation and pure WordNet based disambiguation approaches.