Currently packaging design needs more a computational processing roles and became the fundamental selling art of products. Design of packaging a very subjective and company needs to understand costumer’s behavior.Perceptionand attrantiviness.chalenges arise when marketing in fast moving consumer goods is getting very dynemik and competitive. Computational needs to identify costumer’s perception and attractiviness is unavoidable. In this paper we proposed new methodology to extract and evaluate information elements of packaging design from costumer preferences using computational kansei engineering (KE) approach. The elements of packaging design were extracted from group dis cussion and evaluate centrality and novelty metrick using key element extraction (KEE) Algorithm. Correlation of packaging design elements and kansei words wa obtained with association role mining (ARM). This formulation enabled use to define which packaging design elements are strongly correlated with each kansei/affective words and gives recommendation to designer what kind of packaging to design. In short this proposed methods become a quantification of the art of packaging design that ease a reliable design.