This paper describes our preliminary study of facial expression recognition in order to extract user response information. We used Kinect to get real time facial expressions of the user to extract 6 facial expression categories (neutral, happiness, disgust, surprise, sadness, angry). As for the recognition process, we applied a multi-layer-perceptron to classify the face expressions. A total of 1,912 facial expression data sets were collected from 16 subjects. We performed holdout test using 80% of training data and 20% of test data. The recognition rate without “sadness” feature was around 90%, and the rate using every categories was around 80%. The positive results obtained shows this system as a proper one to measure user preferences in a visual test.