On Forecasting Dynamics In Online Discussion Forums

Online discussion forums are trending as popular platforms that allow asynchronous online interactions through a unique communication structure composed of main threads and the associated replies. In this paper, we present a learning framework – called SocialGrid – for modeling event dynamics in online discussion forums. Using a grid transformation, we explore the possibility of converting the problem of tempo-ral space modeling into the problem of density space modeling. Inspired by the nature of the grid, we leverage a temporal convolution network to learn the dynamics in the density space. Changing the transformation precision, our approach can model the temporal dynamics at different granularities, thereby fulfilling prediction tasks with different needs. Experiments on real-world datasets have shown that our frame-work excels at various prediction tasks compared with other possible approaches.