Copy-and-paste coordination is easy to spot when everybody forgets to change the paste.
Real campaigns are often less polite.
A central organizer can distribute a message, argument, fact sheet, slogan, or sample letter and encourage participants to put it “in their own words.” The result may be dozens or thousands of messages that are not textually identical but still share the same structure, unusual phrases, examples, omissions, and sequence of arguments.
That can make one source look like many independent discoveries.
Rewriting does not create independent origin
Suppose a campaign distributes three points:
- a specific statistic,
- an unusual analogy,
- a call for one exact policy outcome.
One participant copies the text exactly.
Another changes “bad for consumers” to “hurts ordinary customers.” A third rearranges two sentences. A fourth adds a personal greeting.
The messages are now different documents.
They may still have the same source.
A useful historical example of why provenance matters comes from the New York Attorney General’s investigation of the public-comment campaigns surrounding the FCC’s 2017 net-neutrality proceeding. The office reported in 2021 that millions of comments had been fabricated or submitted using identities that did not represent genuine participation. The investigation relied on records from campaign operators and lead generators rather than merely noticing repeated wording. See the New York Attorney General’s report summary.
That is the evidentiary lesson.
Text similarity can point toward coordination.
It does not prove who coordinated it.
Real people use talking points too
Political campaigns, unions, trade groups, charities, product communities, fandoms, and neighborhood organizations routinely give supporters sample language.
That is not automatically deceptive.
A thousand real people can sincerely agree with the same organization and voluntarily use its template.
The stronger Manufactured Consensus problem appears when centrally supplied language is deliberately presented as though it arose independently, especially when the identities, sponsorship, or campaign infrastructure are concealed.
Evidence can include internal instructions, shared documents, distribution emails, campaign software records, payment arrangements, metadata, or admissions from participants.
Without that material, matching phrases are a clue rather than a verdict.
Paraphrasing defeats simple detection
A detector that only searches for exact copies will miss coordinated messages after trivial editing.
A stronger investigation looks for clusters of shared details: rare wording, repeated examples, identical links, synchronized timing, common account infrastructure, or the same claims appearing in the same order.
Even then, language evidence should be paired with provenance when possible.
Manufactured Consensus is not defined by people sounding similar.
Humans imitate one another constantly.
The important question is whether apparent independent agreement was actually produced from a common source that the audience was not allowed to see.