Trump Floods Truth Social With Bizarre Posts On 9/11 Anniversary

HuffPost · left 4 techniques found 5.6% of sentences flagged

Read the original article at HuffPost →

What the model flagged

Analyzed 2026-09-13 04:05 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.

Name Calling 97%

The term 'Dumocrats' is a derogatory label used to mock and discredit political opponents rather than engage with their arguments — for example: 'Dumocrats'

“"Dumocrats"”

Exaggeration/hyperbole 85%

The claim that the country is 'taking in Trillions of Dollars of Economic Development, Investment, and Pure SUCCESS' uses extreme superlatives and capitalisation to overstate economic gains beyond what evidence supports — for example: 'Trillions of Dollars of Economic Development, Investment, and Pure SUCCESS'

“Trillions of Dollars of Economic Development, Investment, and Pure SUCCESS”

Loaded Language 82%

The phrase 'Pure SUCCESS' uses emotionally charged, capitalised language designed to trigger a positive reaction and frame the policy in an uncritical, triumphalist light — for example: 'Pure SUCCESS'

“Pure SUCCESS”

Card Stacking 78%

The statement presents the $5,000 dividend as a near-certain outcome tied to verified-sounding economic activity, while framing critics solely as opponents who 'hope it never happens,' omitting any substantive basis for the criticism — for example: 'criticized by "Dumocrats" who are hoping that it never happens'

“criticized by "Dumocrats" who are hoping that it never happens”

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.