Conceptual graph generation from text documents based on perceptual balance

A conceptual graph generation method is proposed in this paper. A conceptual graph is useful for studying human verbal caring interactions such as counseling, based on an interpersonal psychological approach referred to as 'naive psychology'. We apply the visual assessment of clustering tendency (VAT) to naive psychology, with particular reference to the visual understanding of people. A conceptual graph is constructed from words and sentences selected by morphological analysis. Furthermore, the VAT algorithm produces a visual display that can be used to assess clustering tendencies in a set of persons (notions) by reconstructing a digital image representation of a square relational dissimilarity matrix. This algorithm clearly represents two types of imbalanced situations in naive psychology: namely the crisp and fuzzy situations. In addition, social simulations that utilize several graphs are introduced.