Some years ago, I started to notice on Facebook that friends, family members, people I had not talked to in years, all posting the same arguments using nearly identical phrasing. Not just agreeing on issues, which is normal, but using the same specific words and framing. They had clearly heard it somewhere, probably cable news or talk radio, and were repeating it verbatim.

Sometime later, I started to see news reports about foreign propaganda campaigns. Russian troll farms, Chinese state media, Iranian influence networks. The pattern I noticed on Facebook was not just me being paranoid.

The Party Analogy#

Here is how I think about it. Imagine you are at a party and five people who do not know each other (and who normally disagree about everything) suddenly start making the exact same argument using the exact same phrases. That would be suspicious, right? Either they all heard the same thing somewhere, or someone coordinated their talking points.

That is essentially what I started looking for in news coverage. Not just “is this article biased?” but “are multiple outlets that normally sound very different suddenly sounding the same?”

Why Individual Bias Is Not the Problem#

Any single outlet being biased is expected. Fox leans right, MSNBC leans left, opinion columnists have opinions. That is how our media works. People should know what they are getting by now.

The interesting signal is convergence across the spectrum. When outlets that serve different audiences and hold different editorial positions suddenly align on framing, something unusual is happening. It could be a press release that spread organically, or genuine agreement across the aisle, or actual coordination. The point is that convergence is the signal worth investigating.

I cannot always tell which, but I can tell when it is happening.

What I Built#

Over the past few months I have been building a system called SignalScope to detect these patterns automatically. It monitors news sources across the political spectrum, scores articles for manipulation techniques, and flags when ideologically diverse outlets converge on similar narratives.

SignalScope tracks what “normal” looks like for each outlet, then notices when they deviate from their baseline in the same direction at the same time. A Reuters article that sounds like Daily Wire content is more interesting than a Daily Wire article that sounds like Daily Wire content.

I also look for shared phrases across diverse sources. When NPR, Fox, and Al Jazeera all use the same unusual wording within 48 hours, that specific language came from somewhere. Finding those phrases is like finding a watermark.

What This Is Not#

I want to be clear about what SignalScope doesn’t do.

SignalScope does not determine truth; a coordinated message could still be accurate, and a non-coordinated one could be false. It does not prove intent either, since similar coverage might come from shared source material or genuine consensus rather than coordination. And it is not judging editorial choices. Opinion journalism uses persuasion techniques by design. High scores flag the presence of those techniques, not dishonesty.

Think of it as a metal detector. It beeps when something is there, but you still have to dig to find out what.

What Is Coming#

This is the first post in a series explaining what SignalScope is, and how it works. In future posts I will cover:

• The eight manipulation techniques I score for, and why “high score” does not mean “lying”
• How I detect coordination across ideologically diverse sources (the Cross-Spectrum Coordination Score)
• The limitations of this approach and why they matter

If you are interested in data science, media literacy, influence operations, or just want to understand why your news feed sometimes feels coordinated, then you might find this project interesting.