Minimizing Conflicts of Interest: Optimizing the JSM Program

• Activity Number: 433 - Statistical Approaches in Text Analysis
• Type: Topic-Contributed
• Date/Time: Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
• Sponsor: Text Analysis Interest Group
• Author(s): David Banks and Qiuyi Wu* and Luca Frigau
• Companies: Duke University & SAMSI and University of Rochester and University of Cagliari
• Keywords: Latent Dirichlet Allocation; Topic Modeling; Greedy algorithm; Scheduling

Abstract

Sometimes the Joint Statistical Meetings (JSM) are frustrating to attend, because multiple sessions on the same topic are scheduled at the same time. This paper uses seeded Latent Dirichlet Allocation and a scheduling optimization algorithm to very significantly reduce overlapping content in the 2020 program. Of course, since the pandemic forced the 2020 JSM to be held virtually, our superior schedule was made moot. Nonetheless, this approach may assist in organizing future meetings, both for statistics and for other disciplines.