By Alex Tobias(github) - README here
This is a basic demo of using fasttext's webassembly module to peform sentiment analysis. All work is done in the browser with webassembly, no external requests to any language processing APIs are made.
The model is trained on the Sentiment140 tweet sentiment dataset of 1.6 million tweets. I was able to shrink the model to just 2MB, which is why it's actually possible to load it here.
It's still by no means perfect; and I'm looking into ways to both optimize for size and improve accuracy.
Loading...
Sentiment:
Confidence: