Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://flairnlp.github.io/docs/tutorial-basics/tagging-sentiment below:

Tagging sentiment | flair

This tutorials shows you how to do sentiment analysis in Flair.

Our standard sentiment analysis model uses distilBERT embeddings and was trained over a mix of corpora, notably the Amazon review corpus, and can thus handle a variety of domains and language.

Let's use an example sentence:

from flair.nn import Classifier
from flair.data import Sentence


tagger = Classifier.load('sentiment')


sentence = Sentence('This movie is not at all bad.')


tagger.predict(sentence)


print(sentence)

This should print:

Sentence[8]: "This movie is not at all bad." → POSITIVE (0.9929)

Showing us that the sentence overall is tagged to be of POSITIVE sentiment.

We also offer an RNN-based variant which is faster but less accurate. Use it like this:

from flair.nn import Classifier
from flair.data import Sentence


tagger = Classifier.load('sentiment-fast')


sentence = Sentence('This movie is very bad.')


tagger.predict(sentence)


print(sentence)

This should print:

Sentence[6]: "This movie is very bad." → NEGATIVE (0.9999)

This indicates that the sentence is of NEGATIVE sentiment. As you can see, its the same code as above, just loading the 'sentiment-fast' model instead of 'sentiment'.

We end this section with a list of all models we currently ship with Flair:

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4