The Florida primary from hell

Vox · left 5 techniques found 25.6% of sentences flagged

Read the original article at Vox →

What the model flagged

Analyzed 2026-08-24 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 75%

The phrase 'from hell' is an emotionally charged expression used to frame the Florida primary in an extremely negative light rather than conveying factual information — for example: 'primary from hell'

“from hell”

Name Calling 65%

The label 'socialist' is applied to the candidate in a context where it functions as a political tag that carries negative connotations for many readers, rather than as a neutral policy descriptor — for example: 'a socialist candidate for Senate'

“a socialist candidate for Senate”

Black-And-White Fallacy 70%

The framing presents the race as a binary choice between two extremists with no acknowledgment of nuance or other perspectives, implying voters had only two equally objectionable options — for example: 'pitted an open Islamophobe... against an avowed antisemite'

“pitted an open Islamophobe... against an avowed antisemite”

Scapegoating 75%

The sentence attributes the electoral outcome to a broad negative characteristic ascribed to a significant share of an entire political group, blaming Republicans collectively for holding bigoted views — for example: 'a significant share of Republicans hold Islamophobic or antisemitic opinions'

“a significant share of Republicans hold Islamophobic or antisemitic opinions”

Appeal To Fear 89%

Anxiety about threats or dire consequences used to override rational analysis.

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.