Abstract:
Virality of online content on social networking websites is an important but esoteric phenomenon often studied in elds like marketing, psychology and data mining. In this
project, I have studied viral content from a computer vision and natural language perspective. I have introduced a new dataset from Twitter for studying virality and de ned an annotation score using Twitter metadata. I have also trained a deep learning Siamese model to predict virality of individual posts using relative virality in pairs of posts.
