Near neighbor explorations for keyword-based semantic searches using RDF summary graph

Currently, the most common method to access and utilize data on the Web is through the use of search engines. Classical Information Retrieval (IR) techniques, which the search engines depend on, have many limitations due to the string search mechanism. The problem is that these search techniques are not aware of the context of data on the Web. The underlying reason is the data on the Web was conventionally published as dumps of raw data in various file formats or wrapped in HTML markup. These data representations do not retain a substantial part of the semantics of the underlying data. The Semantic Web, also considered as Web 3.0, began to emerge as its standards and technologies developed rapidly in the recent years. With the continuing development of Semantic Web technologies, there has been significant progress including explicit semantics with data on the Web in RDF data model.;This dissertation proposes a semantic search framework to support efficient keyword-based semantic search on RDF data utilizing near neighbor explorations. Also, a pairwise entity similarity metric is proposed for calculating the similarities of entities in the RDF graph. Additionally, we introduce a novel algorithm for generating the summary graph structure, which helps reduce the computational complexity for graph explorations automatically from underlying RDF data using the pairwise entity similarity metric. The framework augments the search results with the resources in close proximity by utilizing the entity type semantics. Along with the search results, the system generates a relevance confidence score measuring the inferred semantic relatedness of returned entities based on the degree of similarity. Furthermore, the evaluations assessing the effectiveness of the framework and the accuracy of the results are presented.