摘要

Crowdsourced live video broadcasting services, such as Twitch and YouTube Live, are becoming increasingly popular. In such a service, viewers are allowed to perform rich interactions, such as posting comments and donating monetary virtual gifts, while watching videos. Understanding viewer interactions is essential for people to comprehend the production and consumption of the crowdsourced live video content and improve the service. However, the basic characteristics of the viewer interactions are still unknown. In this paper, we present a comprehensive measurement study of the viewer interactions on Douyu, a popular crowdsourced live video broadcasting website in China. Our measurement spans four months and contains comment posting and virtual gift donating interactions from tens of millions of viewers in hundreds of thousands of channels. Based on the measurement data, we carry out a content analysis on danmu comments and characterize the patterns of the viewer interactions. We build a suite of models for capturing the gift donating process, viewer activity, and channel popularity. We further analyze the influences of the broadcaster's behavioral factors on a channel's popularity and present methodologies for popularity predicting. Our measurement and analysis have important implications on the design and business policy of the crowdsourced live video broadcasting services.