– The focus in ICT development has shifted from performance to maximization of tangibility. In particular, the interests in emotion-based services increase and more attention is paid to improving the quality of service and maximizing tangibility. Hence, it is necessary to model human emotions and utilize inferred emotions for services in order to enhance the quality of emotion-based personalized services. To this end, this study aims to model personalized emotional space by means of V-A emotion model and to suggest a fuzzy-based emotion inference method.
– This study takes advantage of V-A emotion model, AHP and fuzzy integral technique to implement an emotion inference based on the quantitative evaluation and systematic expression of human emotions. By means of AHP, the personalized V-A emotion model was established. Fuzzy measure and Choquet integral methods were applied for emotion inference based on the inputs of valence and arousal (V-A) values, with the results evaluated in an experiment.
– Thayer's emotion model structures 12 human emotions in reference to V-A values. This structure, however, may differ depending on individuals, and thus a method to measure and express it appropriately is necessary. This study evaluates the relative weight of 12 emotions based on AHP and regularizes them to compose the personalized V-A emotional space by drafting the V-A model. In addition, fuzzy integral-based emotion inference has been tested in reference to the V-A values on the established V-A emotion space.
– Fuzzy integral-based emotion inference has been tested in reference to the V-A values on the established personalized emotion space.
