Saved in:
Bibliographic Details
Main Authors: Zhao, Hangqi, Li, Jay, Bhattacharya, Abhiruchi, Ni, Cong, Yeung, Jason, Ye, Jinchao, Yang, Kai, Malu, Akshat, Malik, Manish
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.27131
Tags: Add Tag
No Tags, Be the first to tag this record!
_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