Context-aware Semantics-based Information Retrieval

Keßler Carsten

Abstract

Information retrieval can benefit from contextual information to adapt the results to a user’s current situation and preferences. Semantics-based retrieval is especially challenging because a change in context may require modifications to the knowledge base at hand. This book introduces a novel approach for context-aware semantics-based information retrieval that covers two aspects. First, a novel measure for the impact of a contextual aspect on the query results is introduced. This measure allows for the identification of relevant contextual information during work flow and user interface design. Developers can identify which contextual aspects strongly influence the outcome of the retrieval task and should therefore be in the user’s focus. Second, a method for the integration of contextual information with semantics-based knowledge bases is put forward. Starting from qualitative data on the Semantic Web, the book develops a rulebased implementation for the integration of quantitative contextual information from the Sensor Web. This approach establishes an explicit link between an ontology and the dynamic sensor data.