Leveraging Consensus Effect to Optimize Ranking in Online Discussion Boards
Abstract
Online discussion platforms (often referred to as discussion boards) are designed for facilitating discussions between users. To stimulate engagement (e.g., participation in the discussion), these platforms suggest arriving users a ranked list of existing discussion comments. In this paper we formalize the level of consensus in the discussion and study its impact on engagement, and how it could be leveraged by ranking algorithms to increase engagement along the discussion path. We collaborate with a platform who is a global leader for supporting discussions in education settings. Analyzing data from online discussions, we identify and validate the level of consensus in the discussion as a new engagement driver. The presence of consensus effect suggests that ranking algorithms should consider not only comments that would induce engagement in present period, but also ones that would maximize future engagement by managing the desired level of consensus. Based on this insight, we propose a new dynamic model for ranking optimization, and a practical class of intuitive algorithms that, among other factors, account for the level of consensus when prescribing ranking that maximize engagement along the discussion path. In a randomized experiment consisting of 100 discussions held in an education setting, our proposed algorithm outperformed the approach used in current practice (that does not actively manage the level of consensus). Our study proposes consensus as an essential factor in user engagement and in the design of user interface in online platforms, and demonstrates the performance improvement that is achievable by leveraging it in the design of ranking algorithms in discussion boards. In doing so, our study also suggests that online platforms may often benefit from rankings that build debate as opposed to an “echo chamber” of consensus.
Bio
Yonatan Gur is an Associate Professor of Operations, Information and Technology at Stanford Graduate School of Business. His research addresses dynamic optimization in uncertain environments with applications in platform and market analytics. His work aims to elucidate salient features in the design and analysis of content platforms, by adapting and synergizing ideas from the operations research and machine learning disciplines together with empirical data analysis. Yonatan’s research has been recognized by several awards, including Informs Lanchester Prize. Prior to joining Stanford, Yonatan received his PhD in Decision, Risk, and Operations from Columbia Business School. He also holds a B.Sc. degree from the School of Physics and Astronomy and an M.Sc. from the School of Mathematical Sciences, Tel Aviv University.
Link to paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4215596
