Recommender systems on online platforms are often accused of polarizing user attention and consumption. We examine this phenomenon using a quasi-experiment conducted by Zhihu, the largest online knowledge-sharing platform (or Q&A community) in China. Zhihu originally used a content-based filtering algorithm, which recommends content to users based on the topics to which each user has subscribed. After more than a year, Zhihu moved to a social filtering algorithm, which recommends content with which users’ social connections are already engaged. We find that this algorithm change increased the creation of social ties by approximately 15% but decreased question subscriptions (answer contributions) by 20% (23%). We show that users’ increased social interests mainly involved following popular users, leading to a greater concentration of social interests on the platform. However, we find that users’ topical interests became less concentrated, as popular topics received significantly fewer subscribers than unpopular topics. We explain these findings by exploring their underlying mechanism. We show that compared with content-based filtering algorithms, social filtering algorithms are more likely to expose general users to content consumed by their followees, who are more interested in niche topics than general users.
The common belief about the growing medium of livestreaming is that its value lies in its "live" component. In this paper, we leverage data from a large livestreaming platform to examine this belief. We are able to do this as this platform also allows viewers to purchase the recorded version of the livestream. We summarize the value of livestreaming content by estimating how demand responds to price before, on the day of, and after the livestream. We do this by proposing a generalized Orthogonal Random Forest framework. This framework allows us to estimate heterogeneous treatment effects in the presence of high-dimensional confounders whose relationships with the treatment policy (i.e., price) are complex but partially known. We find significant dynamics in the price elasticity of demand over the temporal distance to the scheduled livestreaming day and after. Specifically, demand gradually becomes less price sensitive over time to the livestreaming day and is inelastic on the livestreaming day. Over the post-livestream period, demand is still sensitive to price, but much less than the pre-livestream period. This indicates that the vlaue of livestreaming persists beyond the live component. Finally, we provide suggestive evidence for the likely mechanisms driving our results. These are quality uncertainty reduction for the patterns pre-and post-livestream and the potential of real-time interaction with the creator on the day of the livestream.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.