Interpretation Method of Transformation Matrix Clarifying Relationships between Impression Factors of Multimedia Data

Abstract

This paper proposes a method of interpreting a transformation matrix of the factor loading matrixes obtained through factor analysis often used in affective engineering. A transformation matrix transforms a factor loading matrix of a data set to another one of another data set, and vice versa. It represents the relationship between two sets of factors. A transformation matrix is decomposed into a rotation matrix and a mapping one. It is shown that these two matrixes could be decided by specifying a non-corresponding factor in the factors of two data sets. This enables us to easily interpret the meaning of the transformation matrix.