MVP: Winning Solution to SMP Challenge 2025 Video Track

TL;DR

This paper introduces MVP, a multimodal model that predicts social media video popularity by integrating deep video features, user metadata, and contextual data, achieving top performance in the SMP Challenge 2025.

Contribution

The paper presents a novel multimodal framework combining deep features, metadata, and preprocessing techniques for accurate video popularity prediction.

Findings

Ranked first in SMP Challenge 2025 Video Track

Effective integration of multimodal data improves prediction accuracy

Robust preprocessing enhances model reliability

Abstract

Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, trend detection, and audience engagement. In this paper, we present Multimodal Video Predictor (MVP), our winning solution to the Video Track of the SMP Challenge 2025. MVP constructs expressive post representations by integrating deep video features extracted from pretrained models with user metadata and contextual information. The framework applies systematic preprocessing techniques, including log-transformations and outlier removal, to improve model robustness. A gradient-boosted regression model is trained to capture complex patterns across modalities. Our approach ranked first in the official evaluation of the Video Track, demonstrating its effectiveness and reliability for multimodal video popularity prediction on social platforms. The source code is available at https://anonymous.4open.science/r/SMPDVideo.