The effect of in-person conferences on the diffusion of ideas

As the academic community debates the future of in-person conferences, it is important to understand how effective they are at diffusing ideas. Most previous attempts to analyze this question have struggled to separate causation from correlation and used potentially biased measures like self-reported learning. Here, we propose a novel approach using scheduling conflicts. When multiple presentations of interest to an attendee are scheduled at the same time, the attendee is less able to see them, on average. If seeing presentations influences future research, then conflicting presentations should influence research less than unconflicting ones. Analyzing conflicts in the personalized schedules of 1960 attendees of 20 computer science conferences reveals that when an attendee is able to see a paper presentation, she is almost twice as likely to cite the paper in her future work. The effect is robust to underlying differences between attendees, papers, and paper authors, and is even larger for a stronger measure of influence -- citing the presented paper multiple times. Given the substantial learning effects of in-person presentations, it will be important to ensure that attempts to turn conferences hybrid or virtual do not imperil knowledge diffusion.