Effect of Popularity Shocks on User Behaviour

Abstract

Users often post on content-sharing platforms in the hope of attracting high engagement from viewers. Some posts receive unusual attention and go "viral", eliciting a significant response (likes, views, shares) to the creator in the form of popularity shocks. Past theories have suggested a sense of reputation as one of the key drivers of online activity and the tendency of users to repeat fruitful behaviors. Based on these, we theorize popularity shocks to be linked with changes in the behavior of users. In this paper, we propose a framework to study the changes in user activity in terms of frequency of posting and content posted around popularity shocks. Further, given the sudden nature of their occurrence, we look into the survival durations of effects associated with these shocks. We observe that popularity shocks lead to an increase in the posting frequency of users, and users alter their content to match with the one which resulted in the shock. Also, it is found that shocks are tough to maintain, with effects fading within a few days for most users. High response from viewers and diversification of content posted is found to be linked with longer survival durations of the shock effects. We believe our work fills the gap related to observing users' online behavior exposed to sudden popularity and has widespread implications for platforms, users, and brands involved in marketing on such platforms.

Depression is associated with higher sensitivity to social media rewards

“…For example, a reinforcement-learning account of motivation (24) predicts that a higher rate of rewards (e.g., more likes per post, on average) should make posting more valuable (i.e., more worth the effort required to post and also worth giving up other rewards in place of posting), leading users to post more frequently in the near future. This prediction has been supported in several social media datasets (25,26), including through computational modeling (27). Moreover, receiving more rewards for posts of a certain type should lead users to post similar posts in the future, as demonstrated in recent studies (26,28).…”

Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication

“…On the other hand, employees who are, on average, likely to email many colleagues outside their immediate clique are less likely to receive replies. These insights can generalize to understanding communication behavior on other small-world networks, such as social media platforms, where research on the virality of content [75,76], hot streaks in user popularity [77], and their consequences for user and community behavior [78,79] all discuss the importance of social network features in understanding and modeling communication cascades.…”

Understanding Community Resilience: Quantifying the Effects of Sudden Popularity via Algorithmic Curation

“…Empirical studies have also predicted what content goes viral on platforms like X, formerly Twitter, and YouTube (Figueiredo, Benevenuto, and Almeida 2011;Weng, Menczer, and Ahn 2013). Recent research has also examined the consequences of popularity shocks on online users (Gurjar et al 2022).…”

“…Algorithms that cause popularity spikes are often opaque about how they operate (Eslami et al 2015), and thus create unexpected moments of popularity or virality. Prior work on virality focuses on the content that became viral (Berger and Milkman 2012) or the users who create content (Gurjar et al 2022).…”