While mobile social apps have become increasingly important in people's daily life, we have limited understanding on what motivates users to engage with these apps. In this paper, we answer the question whether users' in-app activity patterns help inform their future app engagement (e.g., active days in a future time window)? Previous studies on predicting user app engagement mainly focus on various macroscopic features (e.g., time-series of activity frequency), while ignoring fine-grained inter-dependencies between different in-app actions at the microscopic level. Here we propose to formalize individual user's in-app action transition patterns as a temporally evolving action graph, and analyze its characteristics in terms of informing future user engagement. Our analysis suggested that action graphs are able to characterize user behavior patterns and inform future engagement. We derive a number of high-order graph features to capture in-app usage patterns and construct interpretable models for predicting trends of engagement changes and active rates. To further enhance predictive power, we design an end-to-end, multi-channel neural model to encode temporal action graphs, activity sequences, and other macroscopic features. Experiments on predicting user engagement for 150k Snapchat new users over a 28-day period demonstrate the effectiveness of the proposed models. The prediction framework is deployed at Snapchat to deliver real world business insights. Our proposed framework is also general and can be applied to other social app platforms 1 .

The Covid-19 pandemic has created large shifts in how people stay connected with each other in lieu of social distancing and isolation measures. More and more, individuals have turned to online communications as a necessary replacement for in-person interaction. Despite this, the research community has little understanding of how online communications have been influenced by the offline impacts of Covid-19. Our work touches upon this topic. Specifically, we study research questions around the impact of Covid-19 on online public and private sharing propensity, its influence on online communication homophily, and correlations between online communication and offline case severity in the United States. To do so, we study the usage patterns of 79 million US-based users on Snapchat, a large, leading mobile multimedia-driven social sharing platform. Our findings suggest that Covid-19 has increased propensity to privately communicate with friends, while decreasing propensity to publicly share content when users are out-and-about. Moreover, online communications have observed a marked decrease in baseline homophily across locations, ages and genders, with relative increases in cross-group communications. Finally, we observe that increased offline positive Covid-19 case severity in US states is associated with widening gaps between across-state and within-state communication increases after the onset of Covid-19, as well as marked declines in public sharing. We hope our findings drive further interest and work on online communication changes during pandemics and other extended times of crisis.

No abstract