The impact of the trade war between the U.S. and Canada
Read the original article at NPR →
What the model flagged
Analyzed 2026-08-27 04:01 UTC. Articles are sometimes updated after publication — if a quote below isn't in the current version, the piece has changed since.
Findings may include language the outlet is quoting rather than asserting. We flag manipulation techniques wherever they appear, including inside quotations — so check each quote against the original before drawing a conclusion about the outlet.
Loaded Language 93%
Emotionally charged words chosen to trigger a reaction rather than convey facts.
Name Calling 90%
Derogatory labels used to discredit a person or group rather than address their arguments.
Repetition 80%
'It is impacting us' repeats the substance of sentence 8 ('it's impacting us') almost verbatim for rhetorical emphasis — for example: 'And it's impacting us. It is impacting us in Michigan.'
“It is impacting us in Michigan”
Exaggeration/hyperbole 65%
Calling Gordie Howe 'one of the greatest hockey players in the United States of America' slightly mischaracterizes him — he was a Canadian-born player celebrated in both countries — to heighten the irony of the tariff, overstating the U.S. connection — for example: 'one of the greatest hockey players in the United States of America'
“one of the greatest hockey players in the United States of America”
Appeal To Fear 87%
Anxiety about threats or dire consequences used to override rational analysis.
False Equivalence 65%
Implicitly contrasts Canada favorably with Mexico by listing Mexico's alleged lack of labor, safety, and environmental standards, suggesting the U.S. is treating a worse actor better — this framing oversimplifies complex trade relationships — for example: 'they are not the same country as Mexico - which, quite frankly, we are treating better'
“they are not the same country as Mexico - which, quite frankly, we are treating better - in not having labor standards, not having safety standards, not having environmental standards”
Analyzed automatically with Semblen's fine-tuned model. These are manipulation techniques, not political tilt — and finding one is not a claim that the article is false. The model has known false positives on strong-but-legitimate language, so treat each finding as a prompt to read closely, not a verdict. How articles are chosen →