Pay Attention to Virality: understanding popularity of social media videos with the attention mechanism
This provides media content creators with more intuitive insights into what makes videos popular, though it is incremental in improving interpretability rather than prediction performance.
The paper tackles the problem of predicting social media video popularity by focusing on interpretability, combining Grad-CAM visualization with a soft attention mechanism to understand how individual video parts influence popularity scores, achieving competitive prediction accuracy.
Predicting popularity of social media videos before they are published is a challenging task, mainly due to the complexity of content distribution network as well as the number of factors that play part in this process. As solving this task provides tremendous help for media content creators, many successful methods were proposed to solve this problem with machine learning. In this work, we change the viewpoint and postulate that it is not only the predicted popularity that matters, but also, maybe even more importantly, understanding of how individual parts influence the final popularity score. To that end, we propose to combine the Grad-CAM visualization method with a soft attention mechanism. Our preliminary results show that this approach allows for more intuitive interpretation of the content impact on video popularity, while achieving competitive results in terms of prediction accuracy.