Contextual personalized searching across a hierarchy of nodes of a knowledge base

Information retrieval systems face challenging problems with delivering highly relevant and highly inclusive search results in response to a user's query. Contextual personalized information retrieval uses a set of integrated methodologies that can combine automatic concept extraction/matching from text, a powerful fuzzy search engine, and a collaborative user preference learning engine to provide accurate and personalized search results. The system and method can normalize documents or information objects into a graph of relationships between concepts (e.g., a knowledge base) and can normalize a search query into the same graph as a set of search criteria. The search can be executed using this graph and using indexes of concepts of the graph, and the results can be scored and presented to the user. User feedback (e.g., explicit and implicit feedback) can be collected to improve future searches.