Clarrus groups and analyses news coverage by comparing how multiple outlets report on the same underlying event.
Articles are continuously collected from a wide range of established news organisations across the political spectrum. These articles are clustered into stories using semantic similarity, recency, and shared subject matter.
For each story, Clarrus examines:
Consensus: Where reporting aligns across sources.
Divergence: Where framing and emphasis differ.
Bias spread: The distribution of outlets across the political spectrum.
Signals: What to watch next, based on coverage trajectories.
Clarrus does not generate or alter facts. It organises reporting to help readers see the broader landscape of coverage.
Clarrus is an independent platform. Our summaries are generated by models and are intended to surface patterns in coverage. They may not capture every nuance of a story.
Bias Scoring Explained
How Clarrus estimates political lean
Clarrus assigns a directional score to outlets based on historical framing patterns, language features, and external media bias assessments. This creates a consistent scale from left to right.
These scores are used to visualise how coverage is distributed across the spectrum - not to label individual stories as biased.
Bias scores are probabilistic and may not reflect every article or editorial stance.
Bias is complex and context-dependent. Clarrus treats bias as a signal, not a verdict.
Editorial Independence
How Clarrus stays neutral
Clarrus does not accept payments or incentives from media outlets, political organisations, or advertisers in exchange for coverage placement.
Our models are designed to surface patterns in coverage without promoting any ideology or worldview.
We believe that transparency and perspective diversity are essential for informed public discourse.
Clarrus is independent and funded by subscriptions. Our goal is to help readers see how the news is being told.