Sentiment Analysis with Flair Text Classifier

This function uses a pre-trained text classifier from the Flair library to predict the sentiment (positive, negative, or neutral) of the given text.

Technology Stack : Flair (Text Analysis Library)

Code Type : Text Classification

Code Difficulty : Intermediate

                
                    
import random
from flair.models import TextClassifier
from flair.data import Sentence
from flair.tokenization import Tokenizer

def predict_sentiment(text):
    # Load a pre-trained text classifier for sentiment analysis
    classifier = TextClassifier.load('en-sentiment')
    
    # Create a sentence from the input text
    sentence = Sentence(text, tokenization=Tokenizer('en'))
    
    # Predict the sentiment of the sentence
    classifier.predict(sentence)
    
    # Return the sentiment and confidence
    return sentence.labels[0].value, sentence.labels[0].score