A Temporal Text Mining Application in Competitive Intelligence

In this paper we describe an application of our approach to temporal text mining in Competitive Intelligence for the biotechnology and pharmaceutical industry. The main objective is to identify changes and trends of associations among entities of interest that appear in text over time. Text Mining (TM) exploits information contained in textual data in various ways, including the type of analyses that are typically performed in Data Mining [17]. Information Extraction (IE) facilitates the semi-automatic creation of metadata repositories from text. Temporal Text mining combines Information Extraction and Data Mining techniques upon textual repositories and incorporates time and ontologies‟ issues. It consists of three main phases; the Information Extraction phase, the ontology driven generalisation of templates and the discovery of associations over time. Treatment of the temporal dimension is essential to our approach since it influences both the annotation part (IE) of the system as well as the mining part.