Will It Go Viral? Grounding Micro-Video Popularity Prediction on the Open Web

2026-05-18

AI Summary

This work addresses the challenge of micro-video popularity prediction, which is heavily influenced by dynamic external trends and cannot be reliably modeled based on content alone. The authors reformulate the task as a prediction problem within an open-web context and introduce WEBSHORTS, the first large-scale dataset that jointly captures micro-videos and their real-time web contexts. They propose SHORTS-CAST, a novel framework that characterizes the external attention landscape at upload time via structured evidence cards, integrates dimension-level reasoning, and employs a delayed-label-driven online adaptation mechanism to jointly model content, contextual signals, and trend evolution. Extensive experiments demonstrate that the proposed approach significantly outperforms existing baselines in both offline and online settings, validating the effectiveness of structured context modeling and trend-aware adaptation.

Abstract

Micro-video popularity prediction (MVPP) forecasts the popularity a newly uploaded short-form video will attract within a fixed number of days after upload. This task supports downstream applications in recommendation, advertising, and creator analytics, yet the problem is hard since virality depends on external trends rather than video content alone. Prior MVPP methods incorporate context by retrieving similar videos from platform-internal corpora, however historical neighbors cannot reveal whether a topic is currently trending, controversial, or already saturated across the open web. To this end, we reformulate MVPP as open-web grounded prediction and introduce WEBSHORTS, the first micro-video dataset that couples 14K videos with real-time open-web context collected at upload time, alongside daily view counts tracked over 7 days. The context for each video is organized as a structured evidence-card that captures the external attention landscape along three complementary web-context dimensions. We further propose SHORTS-CAST, a framework that generates dimension-wise rationales from the evidence-card to guide popularity regression, then adapts at deployment by selectively updating the context-to-popularity mapping when delayed labels reveal genuine trend shifts. In our experiments, SHORTS-CAST consistently outperforms content-only, video corpus retrieval-augmented, and online adaptation baselines under both offline and delayed-label online protocols, confirming that structured web context and trend-aware adaptation are jointly necessary for popularity forecasting under realistic deployment constraints in fast-evolving short-form video ecosystems.

Problem

• micro-video popularity prediction
• open-web context
• virality forecasting
• short-form video
• trend dynamics

Innovation

• open-web grounding
• structured evidence-card
• trend-aware adaptation
• micro-video popularity prediction
• SHORTS-CAST