Please register for this event under the link provided on the right. We will send the link to registered attendees 1 hour before the event starts.
ABSTRACT / Microblogging websites are complex systems where the users interact with each other and generate contents. Some user-generated hashtags become popular after being reposted by a large number of users. New popular contents emerge and the popularity in old popular contents vanishes. On the Chinese microblogging website Sina Weibo, the real-time Hot Search List (HSL) is a reflection of real-time hashtag popularity among all users in the whole system. The patterns of the HSL in the Weibo system are influenced by the circadian behaviors of the users and external factors. In the first part of the talk, we present observed daily patterns in the cumulative number of hashtags, search volume indices and rank diversity. We show a case study on how the COVID-19 pandemic has influenced the emergence of different kinds of hashtags and the ranking on the HSL. In the second part of the talk, we present two emergence mechanisms of the hot topics by showing their network evolution patterns before appearing on the HSL. Accounts with large number of followers are needed to gain popularity in the hashtag propagation. We then investigate the factors that influence the success of the hot topics to become popular and enter the HSL. We observe the importance of the timing of first creation as well as the contents of the posts. In the end, we quantify the fostering effects of the HSL on the hot topics.
BIO / Hao is interested in building mathematical models to solve real world problems. Since undergraduate studies, she has gained mathematical modeling experiences during participation in the Mathematical Contest in Modeling (MCM) and the summer camp in Chinese Academy of Sciences. During her MSc study, many of her research and project experiences have been in an area closely aligned with machine learning of high-dimensional data. Hao's Master's thesis is on learning Bayesian network structure from data. Currently, she is interested in understanding hot topics propagation, popularity prediction and ranking in social media network such as Sina Weibo, the “Twitter of China”.