What AI model powers this?

A two-stage AI pipeline: a fine-tuned transformer model classifies each sentence as manipulative or neutral, then Claude AI identifies the specific technique used (loaded language, name calling, bandwagon appeal, etc.) and explains why it's manipulative. The transformer was trained on thousands of labeled examples with particular coverage of geopolitical framing, historical revisionism, military euphemisms, and economic populist rhetoric.

Biasly — AI-Powered Media Bias & Manipulation Detector

How it works

How Biasly works

Biasly analyzes news articles, videos, and text for media bias and manipulation techniques — loaded language, false equivalence, historical revisionism, geopolitical framing, and more. Unlike a traditional fact-checker, it identifies how language is used to manipulate, not just whether specific claims are true.

Article, text, or video

Paste a URL, drop raw text, or paste a video link — YouTube, TikTok, Instagram, Facebook, or X. For articles we follow pagination automatically and analyze up to 500 paragraphs. For videos we analyze the transcript in 1-minute segments.

Two-stage AI analysis

A fine-tuned transformer classifies each sentence as manipulative or neutral. For flagged sentences, Claude AI identifies the specific technique and explains why it's manipulative — no generic labels, just precise analysis.

See exactly what's flagged

Flagged sentences are highlighted in red. Hover or tap any paragraph to see which technique was used, which specific sentences triggered the flag, and a plain-English explanation of why it's manipulative.

What we detect

18 manipulation techniques, automatically identified

Manipulation rarely announces itself. These are the patterns our AI is trained to catch — and explain.

Loaded Language

Emotionally charged words that trigger fear, anger, or contempt rather than informing.

"The radical extremists are destroying our way of life."

Name Calling / Ad Hominem

Attacking a person or group with derogatory labels to discredit them without engaging their argument.

"Only a fool or a traitor would support this policy."

Appeal to Fear

Exaggerating threats to override rational analysis and demand immediate action.

"Our children will grow up in a totalitarian nightmare if we allow this."

Bandwagon Appeal

Pressuring agreement by claiming everyone is already on board, suppressing independent thought.

"Millions of patriots have already joined the movement — are you with us?"

False Urgency

Manufactured time pressure that discourages careful analysis and demands immediate compliance.

"We must act now — every hour we wait, the situation becomes more catastrophic."

Black-and-White Fallacy

Presenting only two extreme options when a range of alternatives actually exists.

"You're either with us or you're helping the enemy."

Historical Revisionism

Rewriting or minimizing established historical facts to serve a current narrative.

"Colonial rule brought stability and progress to underdeveloped peoples."

War Crime Euphemisms

Sanitized language that obscures documented violations of international law.

"The operation resulted in unavoidable collateral damage."

False Equivalence

Creating artificial moral balance between actions that are not morally comparable.

"Both sides have committed atrocities, so who are we to judge?"

Geopolitical Framing

Describing a conflict using one side's preferred framing as if it were neutral fact.

"Russia's special military operation to denazify Ukraine continues."

Appeal to Prejudice

Exploiting existing biases against an ethnic, religious, or social group to build support.

"These people have never shared our values and never will."

Conspiracy Appeal

Attributing events to secret powerful forces to explain away inconvenient facts.

"The mainstream media is hiding what's really happening — do your own research."

Exaggeration / Hyperbole

Dramatic overstatement that distorts scale and severity to heighten emotional impact.

"This is the most catastrophic betrayal in the entire history of our nation."

Victim Blaming

Language that shifts moral responsibility onto the victims of violence or oppression.

"They brought this upon themselves by refusing to cooperate."

Genocide Denial

Minimizing, denying, or reframing documented atrocities and mass violence.

"The so-called genocide is just enemy propaganda and exaggeration."

Scare Quotes / Dog Whistle

Quotation marks or coded language used to cast doubt on a term without directly arguing against it.

"The 'experts' want you to believe this poses no threat to your community."

Repetition

Deliberately repeating charged words or phrases to make a claim feel more established than it is.

"Crime is up. Crime is everywhere. Crime has never been this bad. It's a crime wave."

Whataboutism

Deflecting criticism by pointing to opponents' wrongdoing instead of addressing the original accusation.

"Why are you asking about our record? Look what the other side did for four years."

Example analysis

See it in action

Biasly catches manipulation across the political spectrum — international conflicts, domestic politics, left-leaning and right-leaning media alike.

BIAS DETECTED

High Risk

3 of 5 sentences flagged (60%)

88%

confidence

Article hover or tap any paragraph for analysis 3 flagged

Russia's special military operation to denazify Ukraine continues as heroic soldiers defend the motherland from Western aggression.

The United Nations documented over 10,000 civilian deaths in Ukraine since the conflict began in February 2022.

The radical left's open-border agenda is flooding our communities with crime and destroying everything hardworking Americans have built.

Border Patrol recorded 2.4 million migrant encounters at the southern border in fiscal year 2023, according to official figures.

Republicans are waging an all-out war on democracy itself, dismantling the very institutions that protect our most fundamental rights.

FAQ

Frequently Asked Questions

Is this tool politically biased?

The model is trained on documented manipulation techniques — patterns identified by media literacy researchers — not on political positions. A sentence that uses loaded language is flagged whether it comes from the left or right. The model does have stronger coverage of geopolitical conflicts (Israel-Palestine, Ukraine-Russia) where historical context manipulation is especially common.

How accurate is it?

On our labeled evaluation set of 50 difficult sentences, the model achieves 100% accuracy at a confidence threshold of 0.95. In real-world use, you'll see both false positives (strong legitimate opinion flagged) and false negatives (subtle manipulation missed). Treat results as a starting point for critical thinking, not a final verdict.

What makes this different from a fact-checker?

Fact-checkers verify specific claims against evidence. This tool identifies techniques — ways language is used to manipulate rather than inform. A sentence can be factually accurate and still use manipulative framing. Both approaches are complementary.

Why can't I analyze NYTimes or Washington Post articles?

Major newspapers block automated access from server IPs. For paywalled or protected sites, copy and paste the article text directly into the text analysis mode.

What model powers this?

A two-stage AI pipeline. First, a fine-tuned transformer model (trained on thousands of labeled examples of biased and neutral text) classifies each sentence. Then, for flagged sentences, Claude AI identifies the specific manipulation technique and explains the reasoning — so you get a precise, readable explanation rather than just a label. The transformer has particularly strong coverage of geopolitical framing, historical revisionism, military euphemisms, and economic populist rhetoric.

Can it analyze videos?

Yes. Paste a video URL into the Video tab — YouTube, TikTok, Instagram, Facebook, and X are all supported. We fetch the transcript and analyze it in 1-minute segments, showing timestamps alongside each verdict so you can jump straight to the flagged moments. Videos without captions or transcripts aren't supported yet.

Can it handle long articles and live blogs?

Yes. For URL analysis, we automatically follow pagination links and analyze up to 500 paragraphs across up to 5 pages — including live blogs like the Guardian that use block-based pagination.

Does this article — or video — contain bias or manipulation?