A User-Centric Multi-Context Hybrid Reasoning Information Retrieval Model

Abstract

Information Retrieval (IR) has been in existence since the 1940s and is impossible to do without. However, research has shown that current information retrieval models do not consider sufficient contexts leading to users in different contexts retrieving the same results. Using a restaurant use case, we propose a user-centric multi-context hybrid reasoning Information Retrieval model to improve the accuracy of retrieved results. Our proposed model uses a hybrid reasoning model of ontology, rules and unsupervised machine learning, considers 14 contexts grouped into user, environmental and database-specific context and considers related domains to the food domain. The result shows that our proposed model outperformed the existing models (location and text-based IR) objectively by 33%.  The results suggest that the consideration of a wider range of contexts, a hybrid reasoning model and the consideration of related domains would improve context-based information retrieval significantly.