House passes Russia sanctions, sending bill named for Lindsey Graham to Trump's desk
Read the original article at NPR →
What the model flagged
Analyzed 2026-09-17 04:00 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.
Glittering Generalities 80%
The phrase 'moral issue' and 'moral courage' use vague, emotionally positive language to frame a political position as a matter of virtue without specifying what actions are required — for example: invoking 'moral courage' as a rhetorical flourish.
“moral issue that requires moral courage”
False Urgency 70%
The phrase 'did everything possible to end this war' implies an urgent, all-or-nothing imperative to act maximally, pressuring deliberation — for example: 'everything possible' frames inaction as moral failure.
“did everything possible to end this war”
Appeal To Fear 70%
Invoking 'the threat' without specification creates anxiety about an unnamed danger to justify action — for example: 'we understood the threat' implies grave consequences if the threat is ignored.
“we understood the threat”
Loaded Language 85%
The phrase 'cripple the Russian war machine' uses emotionally charged, violent imagery to frame military support in stark terms — for example: 'cripple' and 'war machine' are visceral, dehumanising descriptors.
“cripple the Russian war machine”
Black-And-White Fallacy 65%
The framing implies that crippling the Russian war machine is the singular courageous and right path, leaving no room for alternative approaches — for example: 'the courage to do what was right' implies only one correct option exists.
“the courage to do what was right”
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 →