Proceedings of the Eleventh Annual Acquisition Research Symposium, Thursday Sessions Volume II. Lexical Link Analysis Application: Improving Web Service to Acquisition Visibility Portal Phase II

Abstract

We define awareness as the cognitive interface between decision-makers and a complex system, expressed in a range of terms or features, or specific vocabulary or lexicon, to describe the attributes and surrounding environment of the system. Lexical Link Analysis (LLA) is a form of text mining in which word meanings represented in lexical terms (e.g., word pairs) can be represented as if they are in a community of a word network. In the past, we have explored how LLA systematically and automatically discovers new patterns that were previously unknown, and identifies data dependencies from large-scale defense acquisition data of multiple programs that might be indicators for program or investment performances in defense acquisition decision-making and research communities. We also started to apply LLA to improve our understanding of the quality of the data by comparing categories of information and by detecting data overlaps, inconsistency, and gaps from a single program point of view. The Acquisition Visibility Portal (AVP) is a critical tool that provides the DoD-wide acquisition community with authoritative and accurate data services via interfaces to Defense Technical Center (DTIC) and Defense Acquisition Management Information Retrieval (DAMIR) for programs (e.g., major defense acquisition programs [MDAPs], acquisition category II [ACATII] programs) with milestones, costs, schedules and performance data, selected acquisition reports (SAR), acquisition strategy reports (ASR), the systems engineering plans (SEP), the test & evaluation master plans (TEMP), and the defense acquisition executive summary (DAES), among others. The major advantage of using LLA is to apply automation to reveal and depict—to decisionmakers— the correlations, associations, and program gaps across all the programs in the AVP over many years. This enables strategic understanding of data gaps and potential trends, and can inform managers what areas might be highly risky for a program and how resource and big data management might affect the desired return on investment (ROI) among projects.