An Efficient Multi-View Multimodal Data Processing Framework for Social Media Popularity Prediction

Abstract

Popularity of social media is an important symbol of its communication power. Predictions of social media popularity have tremendous business and social value. In this paper, we propose an efficient multimodal data processing framework, which can comprehensively extract the multi-view features from multimodal social media data and achieve accurate popularity prediction. We utilize Transformer and sliding window average to extract time series features of posts, utilize CatBoost to calculate the importance of different features, and integrate important features extracted from multiple views for accurate prediction of social media popularity. We evaluate our proposed approach with the Social Media Prediction Dataset. Experimental results show that our approach achieves excellent performance in the social media popularity prediction task.