Sentiment analysis that runs in your browser

distilbert-base-uncased-finetuned-sst-2-english is the workhorse sentiment classifier — 67 MB, and it returns a positive/negative label with a confidence score in a few milliseconds once loaded. Useful for triaging reviews, support tickets or survey free-text without shipping customer comments to a third-party API. A toxicity model (toxic-bert) is available on the same page when you need to flag abusive content rather than polarity.

sentiment analysis onlinefree sentiment analysis tooldistilbert sst-2text classification browserreview sentiment checkertoxicity detection onlineno api sentiment analysis

Frequently asked questions

Does it handle sarcasm or mixed sentiment?

Poorly, like every binary classifier. SST-2 was trained on movie reviews, so it is confident and often wrong on sarcasm, negation-heavy sentences and text that is positive about one thing and negative about another. Treat the score as a signal, not a verdict.

Is my data uploaded to a server?

No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.

Models available for this task

Twitter RoBERTa Sentiment — Xenova/twitter-roberta-base-sentiment-latest, 129 MB, 125M params
DistilBERT SST-2 — Xenova/distilbert-base-uncased-finetuned-sst-2-english, 69 MB, 67M params
Toxic BERT (Detoxify) — Xenova/toxic-bert, 112 MB, 109M params
mBERT Star Rating — Xenova/bert-base-multilingual-uncased-sentiment, 172 MB, 167M params
FinBERT — Xenova/finbert, 112 MB, 109M params
Multilingual Sentiment Student — Xenova/distilbert-base-multilingual-cased-sentiments-student, 140 MB, 135M params

Explore the rest of the playground

Text & language models

LLM chat — Chat with a local LLM running on your own GPU
Text embeddings — Generate text embeddings locally, in the browser
Translation — Translate text offline with a local neural MT model
Summarization — Summarise long text with a model running on your machine
Zero-shot text classification — Classify text into labels you make up on the spot
Named entity recognition — Named entity recognition, running on your own machine
Question answering — Ask questions about a passage, get the exact answer span
Fill-mask — Watch a masked language model guess the missing word

Guides & comparisons

Model catalog — The model catalog: what actually runs in a browser
WebGPU vs WASM — WebGPU vs WebAssembly for running models in a browser
Browser AI vs cloud API — Browser inference vs a hosted API: an honest comparison
Transformers.js vs WebLLM — Transformers.js vs WebLLM
Whisper model sizes — Choosing a Whisper size for browser transcription
fp32 vs q8 vs q4 — Picking a quantization level for browser inference
Why no image generation — Why this playground has no text-to-image generation
FAQ — Frequently asked questions about browser-based AI
About — About this project

This playground needs JavaScript and WebGPU. Models are downloaded to your browser and executed on your own GPU, so there is nothing to show without a script engine. Enable JavaScript, or read the FAQ for what the site does.