Popularity Prediction of Online Petitions using a Multimodal Deep Regression Model

Abstract

Online petitions offer a mechanism for people to initiate a request for change and gather support from others to demonstrate support for the cause. In this work, we model the task of petition popularity using both text and image representations across four different languages. We evaluate our proposed approach using a dataset of 75k petitions from Avaaz.org, and find strong complementarity between text and images.