Mine Your Data: Contrasting Data Mining Approaches to Numeric and Textual Data Sources

Data mining can be defined as exploration and analysis of large quantities of data in order to discover meaningful patterns and rules. For numeric data the process of this discovery is either directed or non-directed based upon whether there is a fact that we wish to explain through models of explanatory variables, or there is a search for patterns that can prove useful. Text mining is a variation on the field of data mining. It is the discovery by computer of new, previously unknown information, by automatically extracting and linking information from different textual sources. In both methods, automated processes help put together information to uncover new meanings or suggest new hypotheses to be explored further, typically by more conventional means of research. But what are the pros and cons of these methods and how does traditional social science data fit in? This joint paper will elaborate on the typologies of data and text mining, and provide examples and typical models that are relevant to social science and business data. The applicability for Data and Computational Grid applications (e-science) will also be highlighted