Skip to content

Count page views and project clicks with PostHog (EU servers)? It loads only if you choose Allow. Privacy

Sentiment Analyzer live preview
All projects

Sentiment Analyzer

Check the tone of a piece of text without a paid NLP subscription.

Gauging sentiment in feedback or social mentions required paid NLP services or a complex model setup for a simple tone check.

Tech Domain · Book Dev|Published|Evidence: Prototype|Next.js, TypeScript

A public prototype demonstrates the interaction; scope and data are intentionally limited.

Case Study

Before

Gauging the tone of feedback or a draft required paid NLP services or a model setup for a simple check.

After

The demo shows a tone label with every contributing word visible, as a hint rather than a verdict.

How it's solved

Built a tone bench on the App shell using a hand-weighted word list with negation, intensifiers and contrast words (lib/sentiment.ts). Paste a sentence to get a positive, negative or neutral label, a score and the matched words. Text stays in the browser.

Trade-offs

A word list, not a model: no confidence scores or batch mode, and it misreads sarcasm and context.

Related Articles

Further reading on related topics from the blog

Related Projects

More in Tech Domain · Book Dev