President makes final push for Darline Graham in trip to ‘Trump country’

The Hill · center 5 techniques found 15.2% of sentences flagged

Read the original article at The Hill →

What the model flagged

Analyzed 2026-08-22 04:02 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 85%

The label 'far left' is used as a derogatory political tag to discredit the candidate rather than address her policy positions — for example: 'far left'

“labeling her as "far left"”

Appeal To Fear 75%

The phrase implies elections are being rigged, creating anxiety about electoral integrity to motivate a specific response — for example: implying that without action the election will be stolen

“too big to rig”

Conspiracy Appeal 82%

The framing implies a hidden coordinated effort to manipulate elections, invoking shadowy actors engaged in fraud — for example: suggesting organized election rigging is occurring

“too big to rig”
“frequent and unfounded claims of election fraud”

Repetition 75%

The claim of impending impeachment is repeated a third time across the three sentences, reinforcing the idea through redundancy rather than adding new information — for example: 'I'm going to be impeached. They're going to impeach me.'

“They're going to impeach me”

Appeal To Prejudice 65%

The phrase implies the accusers are acting irrationally or without legitimate cause, framing the speaker as a victim of an unjust in-group attack to generate sympathy — for example: 'They have no idea why'

“They have no idea why”

Analyzed automatically with Biasly'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.