Optimization of the Non-Linear Formula for Prediction of Subjective Relevance between TV Contents

Abstract

We have developed a new content-finding navigation system “Roaming Navi”, in which subjective relevance between TV contents is accurately predicted by a complex non-linear formula. In order to optimize the formula, it was necessary, but difficult, to obtain enormous reliable subjective data on the relevance between TV contents. To tackle this problem, we proposed a new probabilistic method to handle subjective data, and the validity of the method was confirmed in empirical questionnaire data. Then, we conducted optimization of the prediction formula combining various optimization methods. As a result, the accuracy of the prediction was significantly improved. Moreover, these methods are broadly applicable in the discipline of Kansei engineering.