Skip to content
Book Open access

Dual-Perspective Video Popularity Prediction from Audience Response to Platform Context

Nov 2026 · 0 citations

Abstract

Social media popularity prediction (SMP) estimates the future attention of social posts and supports recommendation, behavior modeling, and platform optimization. Existing multimodal and retrieval-enhanced methods usually map content, creator, and temporal features directly to a final score, but they underrepresent time-varying publication context such as seasonal trends, campaigns, and real-world events. We propose PEAR, a dual-perspective framework for video popularity prediction. PEAR generates unified LLaVA-NeXT descriptions, retrieves semantically similar historical videos, and combines retrieval statistics with structured metadata in a LightGBM audience-side estimator. It then builds event-conditioned context features from semantic compatibility, lexical/hashtag evidence, temporal activation, and context prevalence, and trains a second LightGBM on out-of-fold residuals to refine the base estimate. PEAR achieves a MAPE of 0.1529 and ranks first in the SMP Challenge 2026 Video Track.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.