multilingual-sentiment-analysis-distilbert

Multilingual Sentiment Analysis

This workflow uses the Distilbert-base-multilingual-cased-sentiments  Model tailored specifically for multilingual sentiment analysis. 

Distilbert-base-multilingual-cased-sentiments Model

A model fine-tuned for sentiment analysis in multiple languages. This model is distilled from the zero-shot classification pipeline on the Multilingual Sentiment dataset.

How to use the Financial sentiments Analysis workflow? 

Using Clarifai SDK

Export your PAT as an environment variable. Then, import and initialize the API Client.

Find your PAT in your security settings.

export CLARIFAI_PAT={your personal access token}

Prediction with the workflow

from clarifai.client.workflow import Workflow

workflow_url = 'https://clarifai.com/clarifai/sentiment-analysis/workflows/multilingual-sentiment-analysis-distilbert'

text = 'I love this movie and i would watch it again and again!'

prediction = Workflow(workflow_url).predict_by_bytes(text.encode(), input_type="text")

# Get workflow results
print(prediction.results[0].outputs[-1].data)

Using Workflow

To utilize the Multilingual Sentiment Analysis workflow, you can input text through the Blue Plus Try your own Input button and it will provide whether the sentiment is positive, negative, or neutral.