How it works
1
Clustering
Recently published articles are automatically grouped based on content
similarity.
2
Validation
Each cluster is analyzed for breaking news signals: sudden spikes in
publication frequency, coverage across multiple publishers, and presence
of high-ranking news sources.
3
Deduplication
Duplicate content within clusters is filtered out while preserving source
diversity.
4
Historical analysis
New candidates are compared against recent breaking news to track continuing
stories.
5
AI evaluation
An AI analysis step confirms whether a cluster represents a significant
event.
6
Classification
Clusters meeting the breaking news criteria receive a special flag in the
system.
/breaking_news, you receive the most representative article
from each breaking news cluster. Results are ordered by cluster size, so the
most widely covered stories appear first.
Query endpoint
Response format
Comparison with other endpoints
Use cases
- Media monitoring — quickly identify emerging stories without tracking multiple sources manually.
- Content curation — surface trending stories for newsletters, apps, or websites based on coverage traction.
- Market intelligence — detect potentially market-moving events as they gain media coverage.
- Crisis monitoring — identify sudden surges in coverage about topics of concern.

