CHALLENGES OF MEASURING USER SATISFACTION VIA AUTOMATIC FACIAL EXPRESSION ANALYSIS

Abstract

Quality measurement and improvement have been an important agenda in many organizations to stay competitive. A good quality measurement needs a good instrument and most of the literature on quality service measurement is based on customer’s perception, which is translated into numbers using likert scale. Perception is very subjective and complicated to be translated into numbers. Thus it is important to have a new way of collecting information that is more precise and scientific to make performance measurement more meaningful. Recent advances in image analysis and pattern recognition open up the possibility of automatic detection and classification of emotional and conversational facial signals. Automating facial expression analysis could bring facial expressions into man-machine interaction as a new modality and make interaction tighter and more efficient. The objectives of this work is to measure the satisfaction level of the new students during the registration process at INTEC, Universiti Teknologi MARA via facial expression recognition and highlight the challenges of data collection in the real environment. Two types of instruments were used to gather the data, paper-based questionnaire and image (facial expression) capturing.