Expired50% confidenceFactExact time
Bilibili's video recommendation algorithm comprehensively considers factors such as text relevance between video titles and search terms, historical click-through rates, interaction data (likes, coins, favorites, danmu), and the UP host account's weight.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedCTR remains the first threshold determining whether a YouTube video enters the recommendation pool; a video must first be clicked before it has a chance to be evaluated by subsequent metrics such as retention rate.70% similarUnverifiedMainstream short video platforms (Douyin, Kuaishou, Video Account, etc.) have all deployed content deduplication systems that compare perceptual hash values, keyframe feature fingerprints, audio fingerprints, and other attributes extracted from videos against existing content in the platform's database.68% similarUnverifiedAfter 6–7 iterations of prompts, the application gained complete features including automatic parsing of X/YouTube/Instagram links, a waterfall layout, category filtering, and multi-user collaboration.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49861API
curl https://kongchang.com/api/v1/knowledge/claims/49861MCP
get_claim(id=49861)