OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction

TL;DR

OmniTrend is a unified framework that separately models content appeal and external exposure factors to improve social media popularity prediction and transferability across platforms.

Contribution

It introduces a joint modeling approach that explicitly separates content attractiveness from contextual exposure, enhancing interpretability and cross-platform applicability.

Findings

The framework effectively predicts popularity by combining content and context models.

It demonstrates improved transferability of popularity predictions across different social media platforms.

The approach provides clearer insights into the influence of content and exposure factors.

Abstract

Predicting social media popularity requires understanding both the intrinsic appeal of content and the external context that determines how it is exposed to users. Existing methods focus on content signals but do not separate them from exposure-related patterns, which causes the learned representations to absorb platform-specific visibility effects and weakens both interpretability and cross-platform transfer. This paper introduces OmniTrend, a unified framework that models popularity as the joint outcome of content attractiveness and contextual exposure. The content module learns cross-modal representations from visual, audio, and textual cues to quantify intrinsic appeal, while the context module estimates exposure from exogenous signals such as posting time, author activity, topical trends, and retrieval-based neighborhood statistics. OmniTrend learns separate predictors for content attractiveness and contextual exposure and integrates them in the final popularity estimate, which makes the role of each factor explicit and supports robust transfer across image and video platforms.