Trump imposes sweeping bans on Canadian goods in deepening trade war

UPI · center 4 techniques found 9.5% of sentences flagged

Read the original article at UPI →

What the model flagged

Analyzed 2026-09-09 04:07 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 92%

The phrase 'ripping us off' is emotionally charged slang designed to provoke outrage rather than describe trade policy neutrally — for example: 'ripping us off'

“ripping us off for years”

Conspiracy Appeal 72%

The framing 'what many do not realize' implies a hidden truth being suppressed or overlooked, suggesting the audience is unaware of a secret wrongdoing — for example: 'what many do not realize'

“what many do not realize”

Card Stacking 75%

The sentence presents Canada's procurement restrictions as a one-sided grievance without acknowledging any reciprocal U.S. trade barriers or the complexity of trade agreements — for example: 'banned American Small Businesses and Companies from selling into their Government Procurement Markets'

“banned American Small Businesses and Companies from selling into their Government Procurement Markets”

Exaggeration/hyperbole 70%

Describing the American Government Procurement Market as 'massive' is an emphatic superlative used to amplify the perceived unfairness of the asymmetry — for example: 'the massive American Government Procurement Market'

“the massive American Government Procurement Market”

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 →

Get notified as this improves — new detection models, the browser extension, and outlet scorecards. Occasional email, no spam.