Field information recommendation based on context-aware and collaborative filtering algorithm

Abstract

Personalized recommendation technology is a valid way to solve the problem of “information overload”. In the face the complexity of agricultural field information and problems of farmers’ preference prediction accuracy which is not high, this paper proposes a kind of recommendation algorithm based on context-aware and collaborative filtering (CACF). The algorithm constructs the “user-item-context” 3D user interest model which contains the context information. Through calculating context similarity and adopting pre-filtering paradigm, the 3D model is reduced to “user-item” 2D model. By computing item similarity, it can predict the item rating and generate recommendations. The CACF was applied on the field information recommendation. The experimental results show that the CACF can accomplish higher recommendation precision and efficiency compared with the traditional User-based collaborative filtering algorithm (UBCF), Slope one algorithm (SLOA).