Quality, Relevance and Importance in Information Retrieval with Fuzzy Semantic Networks

We propose a framework for ranking information based on quality, relevance and importance, and argue that a socio-semantic contextual approach that extends topicality can lead to increased value of information retrieval systems. We use Topic Maps to implement our framework, and discuss procedures for calculating the resource ranking. A fuzzy neural network approach is envisioned to complement the process of manual metadata creation.