Prediction of social image popularity dynamics

This paper introduces the new challenge of forecasting the engagement score reached by social images over time. The task to be addressed is hence the estimation, in advance, of the engagement score dynamic over a period of time (e.g., 30 days) by exploiting visual and social features. To this aim, we propose a benchmark dataset that consists of ~20K Flickr images labelled with their engagement scores (i.e., views, comments and favorites) in a period of 30 days from the upload in the social platform. For each image, the dataset also includes user’s and photo’s social features that have been proven to have an influence on the image popularity on Flickr. We also present a method to address the aforementioned problem. The engagement score dynamic is represented as the combination of two properties related to the dynamic and the magnitude of the engagement sequence, referred as shape and scale respectively. The proposed approach models the problem as the combination of two prediction tasks, which are addressed individually. Then, the two outputs are properly combined to obtain the prediction of the whole engagement sequence. Our approach is able to forecast the daily number of views reached by a photo posted on Flickr for a period of 30 days, by exploiting features extracted from the post. This means that the prediction can be performed before posting the photo.