Dependence among terms in vector space model

The vector space model is a mathematical-based model that represents terms, documents and queries by vectors and provides a ranking. In this model, the subspace of interest is formed by a set of pairwise orthogonal term vectors, indicating that terms are mutually independent. However, this is a simplification that doesn´t correspond to the reality. Based on this scenery, we present, in this work, an extension to the vector space model to take into account the correlation between terms. In the proposed model, term vectors are rotated in space geometrically reflecting the dependence semantics among terms. We rotate terms based on a data mining technique called association rules. The retrieval effectiveness of the proposed model is evaluated and the results shows that our model improves in average precision, relative to the standard vector space model, for all collections evaluated, leading to a gain up to 31%.