Automatic Evaluation of Emotion Elicitation oriented to people with intellectual disabilities

People with intellectual disabilities and elderly need physical and intellectual support to ensuring independent living. In our project a new IS system (LAGUNTXO) which adds user affective information oriented to people with intellectual disabilities has been developed. The system integrates a Human Emotion Analysis System (HEAS) which attempts to solve critical situations for this community as block stages. In the development of the HEAS one of the critical issues was to create appropriated databases to train the system due to the difficulty to simulate pre-block stages in laboratory specifically in the case of people with disabilities. A film and real sequences based emotion elicitation database was created. The elicitation material was categorized with features based on discrete emotions and dimensional terms (pleasant, unpleasant). In this work we present the Automatic Evaluation of Emotion Elicitation databases based on Machine Learning classifiers and un-supervised K-means clustering which provides new approaches of emotional answers finally validated by the specialist.