Hacker News Reader

This looks really great with such a simple UI.last year I tried to do a realtime sentiment analysis on twitter messages using TextBlob.It was fast but not very accurate. Can you suggest any other library which might works fast enough on realtime messages.

View on HN

For inference speed I recommend a Naive Bayes model. I've tried this on Twitter messages and got near ~90% accuracy with 3-class (positive, negative, neutral).

The easiest library to do that would probably be scikit-learn with their ComplementNB class: https://scikit-learn.org/stable/modules/generated/sklearn.na...

For the data you can use the SemEval 2017 Task4-A dataset (around ~10K labeled tweets): https://github.com/cbaziotis/datastories-semeval2017-task4/t...

Reply on news.ycombinator.com