Improving the Relevance of a Web Navigation Recommender System Using Categorization of Users' Experience

We propose a method for a recommender system for generating web-navigation suggestions. The purpose of this system is to assist its users by providing them suggestions for possible desired next steps whenever they get stuck in using any software. We are able to achieve this goal by leveraging the principal of 'crowd-sourcing'. Specifically, we leverage the crowd's knowledge under the assumption that there are cohesive groups of experienced and novice users. Therefore, we present an algorithm that measures the right heuristics in order to classify users by their experience, and then relates these users with association rules of web-navigation derived from frequent patterns mining. In this paper we introduce our method, compare it with other current solutions in the field, outline the proposed algorithm, and present an experiment which serves as our proof-of-concept.