Sentiment Tone Classifier

Score reviews, replies and posts positive, negative or mixed, sentence by sentence, with a sentiment model that runs in your browser.

Free, private.

Last updatedHow we build & check our tools

Interactive Tool

This tool runs in your browser and is loading now.

Enter your values once it appears to see your results.

How Sentiment Tone Classifier works

Press Load model once: your browser downloads MobileBERT sentiment classifier (MediaPipe) (33 MB) from this site and keeps it in its cache. Then add your text and press Classify tone. The model runs on this device, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

MobileBERT sentiment classifier (MediaPipe) is a compact BERT model fine-tuned on the Stanford Sentiment Treebank (SST-2), a set of movie-review sentences labelled positive or negative. The tool scores your whole text, then every sentence on its own.

A sentence counts as clearly positive or negative when the model is at least 80% sure. If clearly positive and clearly negative sentences both appear, the overall result is Mixed; otherwise it follows the whole-text score. The most negative and most positive sentences are quoted so you can see what drove the result.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

I love how fast the product is now. The new dashboard saves me an hour a week. But the billing page is confusing, and I still have not had a reply about my renewal.
Overall
Mixed
Sentence balance
1 positive · 1 negative
Most negative sentence
But the billing page is confusing, and I still have not had a reply about my renewal.
Most positive sentence
I love how fast the product is now.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

You can switch models in the tool. Also available: Gemma 4 E2B instruction-tuned (web build) (2.0 GB). The larger language model gives more thorough answers but is a bigger download and needs a stronger device.

ModelDownloadRuns onLicence
MobileBERT sentiment classifier (MediaPipe)26 MBProcessor (WebAssembly)Apache-2.0
Gemma 4 E2B instruction-tuned (web build)2.0 GBGraphics card (WebGPU)Apache-2.0

Limitations

  • The model only knows positive and negative. It does not detect anger, urgency or politeness, and it was trained on movie reviews, so sarcasm, jargon and very short replies can be misread.
  • Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

  • Support triage queues
  • Review monitoring
  • Social post QA
  • Product feedback clustering

Frequently Asked Questions

Common questions about the Sentiment Tone Classifier

No. The model files download from this site once, and then everything runs in your browser tab. The text you enter is never sent to a server, and closing the tab discards it.
From the same team

Stop paying per token — route AI requests to your own GPU

Wide Area AI is a local-first AI gateway: repeated requests hit an edge cache, the rest run free on your own hardware, and the cloud is only a failover. OpenAI-compatible endpoint, free tier.

Start routing — free
VRAM CalculatorCan I Run This AI?AI API Cost CalculatorGPU for Model

Explore More Tools

Explore these related tools for your next step.

ai

LLM GPU Benchmark

Speed test your GPU for AI — measure real memory bandwidth and compute with WebGPU, run an actual LLM in your browser to measure true tokens/sec, and see predicted speeds for every popular model on your hardware.

Try it now
ai

Phishing Email Analyzer

Paste a suspicious email and get an instant phishing risk score — checks for spoofed senders, deceptive links, lookalike domains, urgency tactics, and dangerous attachments. 100% private: nothing is uploaded, with an optional in-browser AI explanation.

Try it now
ai

PII Redactor

Detect and redact personal and sensitive data — emails, SSNs, credit cards, phone numbers, IPs, API keys — from any text or logs before you share them. Runs 100% in your browser; nothing is uploaded.

Try it now
ai

Private AI Summarizer

Summarize any text with AI that runs entirely in your browser — paste an article, contract, or report and get bullet points or a TL;DR. Unlike cloud summarizers, your text is never uploaded.

Try it now
ai

Tokenizer Visualizer — See How LLMs Split Text Into Tokens

Paste any text and watch GPT-4 (cl100k_base) or GPT-4o/o1 (o200k_base) split it into colored token chips, with live token/char/word stats, per-model API cost, and a side-by-side tokenizer comparison. Runs entirely in your browser using the real gpt-tokenizer library — nothing is uploaded.

Try it now
ai

AI GPU Buying Guide: Best GPU for Running Local LLMs

Pick the right GPU for running local LLMs. Choose your target models, quantization, and minimum speed, and get a ranked GPU table with VRAM fit, estimated tokens/sec, and real community benchmark data — all computed in your browser.

Try it now