LLM-Enhanced Topical Trend Detection at Snapchat
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909001503997952 |
|---|---|
| author | Zhao, Hangqi Li, Jay Bhattacharya, Abhiruchi Ni, Cong Yeung, Jason Ye, Jinchao Yang, Kai Malu, Akshat Malik, Manish |
| author_facet | Zhao, Hangqi Li, Jay Bhattacharya, Abhiruchi Ni, Cong Yeung, Jason Ye, Jinchao Yang, Kai Malu, Akshat Malik, Manish |
| contents | Automatic detection of topical trends at scale is both challenging and essential for maintaining a dynamic content ecosystem on social media platforms. In this work, we present a large-scale system for identifying emerging topical trends on Snapchat, one of the world's largest short-video social platforms. Our system integrates multimodal topic extraction, time-series burst detection, and LLM-based consolidation and enrichment to enable accurate and timely trend discovery. To the best of our knowledge, this is the first published end-to-end system for topical trend detection on short-video platforms at production scale. Continuous offline human evaluation over six months demonstrates high precision in identifying meaningful trends. The system has been deployed in production at global scale and applied to downstream surfaces including content ranking and search, driving measurable improvements in content freshness and user experience. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27131 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-Enhanced Topical Trend Detection at Snapchat Zhao, Hangqi Li, Jay Bhattacharya, Abhiruchi Ni, Cong Yeung, Jason Ye, Jinchao Yang, Kai Malu, Akshat Malik, Manish Information Retrieval Automatic detection of topical trends at scale is both challenging and essential for maintaining a dynamic content ecosystem on social media platforms. In this work, we present a large-scale system for identifying emerging topical trends on Snapchat, one of the world's largest short-video social platforms. Our system integrates multimodal topic extraction, time-series burst detection, and LLM-based consolidation and enrichment to enable accurate and timely trend discovery. To the best of our knowledge, this is the first published end-to-end system for topical trend detection on short-video platforms at production scale. Continuous offline human evaluation over six months demonstrates high precision in identifying meaningful trends. The system has been deployed in production at global scale and applied to downstream surfaces including content ranking and search, driving measurable improvements in content freshness and user experience. |
| title | LLM-Enhanced Topical Trend Detection at Snapchat |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.27131 |