Browser Extension for Chrome & Firefox

Read between
the lines.

E-Prime Bias Detector highlights the linguistic patterns that shape how you interpret information — opinion disguised as fact, vague sourcing, emotional manipulation — alongside markers of quality writing. The goal is sharper reading, not prescribed conclusions.

View on GitHub

Every word is a choice.
This tool makes those choices visible.

The extension runs on any web page, highlighting patterns in real time. Here's what a typical analysis looks like:

example-news.com/article/policy-analysis

Experts say the new policy is clearly a step in the right direction. Everyone agrees that change was long overdue.

According to Dr. Chen et al. (2024), the data suggests a possible correlation, though important limitations include the sample size and geographic scope.

Opinion
To-Be Verb
Absolute
Weasel Word
Excellence

What the extension looks for — and why.

Each category targets a specific way language can mislead or demonstrate integrity. The extension doesn't assume any pattern is inherently bad — it makes it visible so you can decide. See the full pattern reference for every word and phrase the extension detects.

Basic Detection

Opinion Words

Subjective language and evaluative terms like "obviously," "terrible," "brilliant" — judgment embedded in description.

To-Be Verbs

E-Prime violations that can create false equivalencies. "This policy is a failure" collapses complex evaluation into identity.

Absolutes

Universal claims like "everyone," "always," "never" — sweeping statements that are almost never literally true.

Advanced Detection

Passive Voice

Constructions that obscure who is responsible. "Mistakes were made" hides who made them.

Weasel Words

Vague attributions like "experts say," "studies show," "people are saying" — authority without accountability.

Presuppositions

Hidden assumptions smuggled into statements as established fact. The embedded premise goes unquestioned.

Probability Language

Words that shape how likely we perceive events to be, often misaligning perception with statistical reality.

Framing & Rhetoric

War Metaphors

Militaristic language applied to non-military topics. Framing everything as a fight constrains how we think about solutions.

Minimizers

Language that downplays significance: "merely," "just," "only." Distorts scale by making things seem smaller than they are.

Maximizers

Exaggeration and hyperbole: "absolutely," "the greatest," "unprecedented." Emphasis substituted for evidence.

Manipulation Tactics

False Balance

Presenting two positions as equally valid when evidence strongly favors one. Creates artificial equivalence.

Euphemisms

Softening language that obscures harsh realities. "Collateral damage" for civilian deaths, "downsizing" for layoffs.

Emotional Manipulation

Language designed to bypass rational evaluation and trigger emotional responses instead of analysis.

Gaslighting

Phrases that undermine confidence in documented facts: "that never happened," "concerns are overblown."

False Dilemmas

Presenting complex situations as binary choices: "you're either with us or against us." Reality is rarely that simple.

What good writing looks like.

Bias detection alone creates cynicism. The excellence system shows what responsible, intellectually honest writing actually looks like — so you can recognize and reward it.

Clear Attribution

Named sources, dates, publication venues, sample sizes. Verifiable claims you can actually check.

"According to Smith et al. (2024), a study of 15,000 participants found..."

Nuanced Language

Acknowledging complexity rather than pretending certainty. "The evidence suggests" rather than "this proves."

"The data might indicate a trend, though alternative explanations exist."

Transparency

Being upfront about limitations, perspective, and uncertainty. Saying "in my opinion" when it is one.

"Important limitations include the sample size and geographic scope."

Constructive Discourse

Building on others' ideas, acknowledging valid counterpoints, inviting dialogue rather than shutting it down.

"Building on Johnson's observation, an additional factor worth considering..."

Evidence-Based Claims

Specific data, methodology references, statistical context. Claims grounded in verifiable information.

"The 95% confidence interval (p < 0.01) across 3 independent studies..."

Install in under a minute.

Pre-built extensions are included in the repo — no build step required. Just clone and load.

1

Clone the repo

Or download it as a ZIP from GitHub.

git clone https://github.com/shadnbob/e-primer.git
2

Load the extension

Chrome: Go to chrome://extensions, enable Developer mode, click "Load unpacked" and select the dist/ folder.

Firefox: Go to about:debugging, click "Load Temporary Add-on" and select dist-firefox/manifest.json.

3

Build from source (optional)

Only needed if you want to modify the extension.

cd e-primer && npm install
npm run build       # Chrome
npm run build:firefox # Firefox