Modeling User Loyalty for Korean Political YouTube Channels

Abstract

In this paper, we propose a model based on user loyalty to understand user behavior. User loyalty is defined based on three factors, which are coverage, duration, and enthusiasm. In particular, we focus on a case study of user loyalty involving South Korean politics in online social networks. Our purpose is to understand user behaviors to help governments and politicians in decision-making. We deploy a web-based system (called TubePlunger) to collect information from Youtube videos and corresponding comments. Our system collects approximately 3M comments of more than 300K users from six channels for the initial dataset and 23 channels for testing the model. Firstly, we separate six channels into two sides: left-wing and right-wing. Based on their comments information in videos of the channel, we recognize the loyalty distribution of users who engaged in online political platforms is sharply polarized. In this step, we only consider the usernames instead of video and comment contents. Secondly, we apply the user loyalty model not only to define which channels of 23 testing channels belong to left-wing or right-wing but also to present the user loyalty distribution. The experimental results show the absolute consistency in user loyalty distribution with left-wing and right-wing in all three mentioned factors.