Integrated Suite of Text and Data Mining Tools - Phase II

摘要

This report summarizes the results of a three-year SBIR project to develop an integrated suite of text and data mining tools. The goal of this project is to provide tools that can help analysts find connections between requirements (as expressed in requirements, documents, or databases) and open- source research literature. An overall approach is outlined, and a step-by-step overview of the work is presented. The tool suite includes parsers for text data sources, metadata extraction, record combining, entity extraction, data normalization, sub-and cross-dataset analysis, multi-field analysis and visualizations, feature selection, XML importers, and indirect link analysis. A set of recommendations for expanding the use of the tools is presented.