Semantic Annotation for Supporting Context-Aware Information Retrieval in the Transportation Project Environmental Review Domain

Although transportation practitioners nowadays have an unprecedented level of access to information, substantial gaps still exist in their ability to efficiently and reliably find the right information, at the right time, for the task or decision at hand. To address this gap, this paper proposes a context-aware information retrieval (IR) approach that can capture and exploit the conceptualization of user needs, decision context, and content meanings in order to support the retrieval of information that is more relevant to decision making. The proposed IR approach includes three primary components: semantic annotation (SA), semantic query processing (SQP), and semantic document ranking (SDR). This paper focuses on SA for IR for supporting the transportation project environmental review (TPER) decision-making process. It proposes an epistemology-based SA algorithm for automatically annotating Web pages in the TPER domain with contextual concepts from an epistemological model. The TPER epistemology is a semantic model for representing and reasoning about information and IR in the TPER domain. In developing the proposed algorithm, a number of shallow and deep SA algorithms were developed and tested. For the shallow SA algorithms, the effects of syntactic expansion and filtering were investigated. For the deep SA algorithms, different semantic similarity (SS) calculation methods were evaluated. All the algorithms were tested on a data set of 1,328 Web pages, which were collected from the Federal Highway Administration (FHWA) Environmental Review Toolkit Web site, and they were evaluated in terms of mean precision (MP) and mean average precision (MAP). The final, proposed SA algorithm achieved over 91% MP and over 86% MAP at the top 10, 20, 30, 40, and 50 documents on the testing data.