Twenty quotes can feel like twenty votes.
They are not.
A writer can search a large social network, forum, comment section, or archive until they find twenty people saying something bizarre.
Put those remarks in one article and the reader sees a wall of apparent agreement.
What the reader does not see is the denominator.
Maybe those twenty comments came from twenty-five people.
Maybe they came from twenty million.
Collections create an implied sample
A headline such as People online are furious about this makes a statistical claim even when no statistics appear.
The supporting evidence may be ten screenshots selected because they were dramatic enough to include.
The quotes can all be authentic.
The impression can still be false.
This is ordinary selection bias applied to public reaction.
Recent research on using social-media users to estimate public opinion shows why caution is necessary. A 2026 study in Public Opinion Quarterly compared a probability sample with a nonprobability sample of Twitter users and found meaningful demographic and attitudinal differences before statistical adjustment. See the study summary in PubMed and the full open-access paper.
A hand-picked collection of colorful posts is far less representative than even a structured nonprobability survey.
The quote can be true while the trend is invented
This distinction matters.
If a person really posted an absurd opinion, quoting them accurately is not fabrication.
The manipulation appears when selection is used to imply prevalence that the evidence does not establish.
Five hostile reviews do not prove customers generally hate a product.
Five glowing comments do not prove universal satisfaction.
Ten extreme political posts do not establish what a country believes.
A montage is evidence that those remarks existed.
It is not automatically evidence that they were typical.
Context needs a denominator
Useful questions include:
- How large was the population searched?
- How were examples selected?
- Were contrary views excluded?
- Did the quotes come from unique people?
- Were they concentrated in one community?
- What time window was used?
- Is the source attempting to describe prevalence or merely illustrate existence?
Sometimes a quote collection is perfectly legitimate.
An article about unusual customer complaints may intentionally collect unusual complaints. A history of a fringe movement may intentionally quote fringe participants.
The problem is not selection itself.
It is hiding the selection while asking the reader to infer frequency.
Manufactured Consensus does not always need fake people.
Sometimes it only needs a real crowd, a search box, and an editor who keeps the twenty quotes that tell the desired story.