NPR · left

Max Miller is refusing to drop his bid for reelection. Here's what voters think

Open the full analysis → Read the original article at NPR →

Flags are about wording, sourcing and context, not whether it’s true or which side is right. How we check

Wording

22%of the article’s sentences use a rhetorical technique

Tap a technique to see where it’s used.

What these techniques mean

Loaded Language Emotionally charged words that push a reaction instead of giving information.Show the first one ↓

Repetition Saying the same point again to make it stick, not to add to it.Show the first one ↓

Appeal to Fear Raising a threat to drive the reader’s view.Show the first one ↓

Name Calling A label used to mock or discredit instead of an argument.Show the first one ↓

Glittering Generalities Vague, approving words with no specific claim behind them.Show the first one ↓

ClaimsCheck the factual claims in this article →

What the model flagged

underlined: technique found; pick one to highlight its words tap a technique for why

“troubled candidate”

↓

Loaded Language · “troubled candidate”Why ›

The word 'troubled' is an emotionally charged descriptor applied to the candidate that goes beyond neutral factual reporting.

“"kramer" ×5” … “"soundbite" ×3”

↓

Repetition · “"kramer" ×5”, “"soundbite" ×3”Why ›

Repeats key words or phrases to hammer ideas into the audience and make them seem more credible through familiarity.

↓

Appeal to FearWhy ›

Creates anxiety and fear to influence decisions rather than using logical reasoning

“He's a womanizer”

↓

Name Calling · “He's a womanizer”Why ›

The quoted voter applies a derogatory label to Miller rather than addressing specific facts or arguments.

“focused on election integrity”

↑

Glittering Generalities · “focused on election integrity”Why ›

The phrase 'election integrity' is used as a vague, positively valenced term to lend legitimacy to the rally without substantive meaning.

Read the original ↗ · Open the full analysis →

↑ Back to the results

Analyzed 2026-08-10 04:00 UTC. Articles are sometimes updated after publication — if a quote here isn't in the current version, the piece has changed since.

Analyzed automatically with Semblen's fine-tuned model. These are rhetorical techniques, not political tilt — and finding one is not a claim that the article is false. Findings include language the outlet is quoting rather than asserting: we flag techniques wherever they appear, so check each quote against the original. 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 →