There is provided an application stored in a computer-readable storage medium for a first terminal to perform a method of providing a video call service, the method including: receiving a first video stream of a first user of the first terminal when the application that provides the video call service is executed; extracting facial feature points of the first user from the first video stream; predicting whether the first user is a bad user by applying distribution information of the facial feature points of the first user to a learning model for bad user identification based on facial feature points of a plurality of users; and controlling display of a component on an execution screen of the application based on a result of the predicting.