Media Security

Image Popularity Prediction in Social Media Using Sentiment and Context Features

Can visual sentiment and context features help to predict which images will become popular?

Images in social networks share different destinies: some are going to become popular while others are going to be completely unnoticed. In this paper we propose to use visual sentiment features together with three novel context features to predict a concise popularity score of social images. Experiments on large scale datasets show the benefits of the proposed features. We report a qualitative analysis of which sentiments seem to be related to good or poor popularity.

View Project

Copyright © MICC Media Integration and Communication Center, University of Firenze, Italy - 2018. Privacy policy