Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms

Abstract

Popularity prediction using social media is an important task because of its wide range of real-world applications such as advertisements, recommendation systems, and trend analysis. However, this task is challenging because social media is affected by multiple factors that cannot be easily modeled (e.g. quality of content, relevance to viewers, real-life events). Usually, other methods adopt the greedy approach to include as many modalities and factors as possible into their model but treat these features equally. To solve this phenomenon, our proposed method leverages the self-attention mechanism to effectively and automatically fuse different features to achieve better performance for the popularity prediction of a post, where the features used in our model can be mainly categorized into two modalities, semantic (text) and numeric features. With extensive experiments and ablation studies on the training and testing data of the challenging ACM Multimedia SMPD 2020 Challenge dataset, the evaluation results demonstrate the effectiveness of the proposed approach as compared with other methods.