A systematic framework for popularity prediction of travel short videos

Sustainable Environment Research · Springer Nature · 2026-08-17 · DOI: 10.1007/s12293-026-00528-z

Аннотация

Travel short videos have become a major channel through which destinations are discovered, evaluated, and socially amplified. Predicting whether a video will become popular is very challenging since the video popularity is jointly determined by content quality, creator-level exposure, and the long-tailed dynamics of online interaction. This paper first develops a comprehensive popularity score from likes, comments, favorites, and shares, where principal component analysis determines data-driven indicator weights and the 80th percentile defines a dynamic popularity boundary. To model tourism-specific content, visual, audio, and textual representations are extracted using TimeSformer, Whisper, and a pre-trained language encoder, respectively. A bottleneck multimodal transformer is developed to constrain cross-modal communication through learnable bottleneck tokens, reducing redundant interactions among scenery frames, background audio, and textual metadata. Finally, a video category-aware mixture-of-experts predictor combines fused content features with traffic metadata to model heterogeneous diffusion mechanisms across tourism themes. Experiments on collected 2,274 real-world travel short videos from TikTok show that the proposed framework achieves 89.45% accuracy and 0.9405 AUC, outperforming a number of baselines. The results suggest that reliable popularity prediction requires both effective multimodal content modeling and explicit treatment of exposure priors.

Читать у издателя →

Похожие статьи