IT-EMOTION-ANALYZER

This is a model for emotion analysis of italian sentences trained on a translated dataset by Google Translator. It maps sentences & paragraphs with 6 emotions which are:

• 0: sadness
• 1: joy
• 2: love
• 3: anger
• 4: fear
• 5: surprise

Model in action

Using this model becomes easy when you have transformers installed:

pip install -U transformers

Then you can use the model like this:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import pipeline

sentences = ["Questa è una frase triste", "Questa è una frase felice", "Questa è una frase di stupore"]

tokenizer = AutoTokenizer.from_pretrained("aiknowyou/it-emotion-analyzer")
model = AutoModelForSequenceClassification.from_pretrained("aiknowyou/it-emotion-analyzer")

emotion_analysis = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
emotion_analysis(sentences)

Obtaining the following result:

[{'label': '0', 'score': 0.9481984972953796},
 {'label': '1', 'score': 0.9299975037574768},
 {'label': '5', 'score': 0.9543816447257996}]

Model Trained Using AutoTrain

• Problem type: Multi-class Classification
• Model ID: 43095109829
• CO2 Emissions (in grams): 0.4489

Validation Metrics

• Loss: 0.566
• Accuracy: 0.828
• Macro F1: 0.828
• Micro F1: 0.828
• Weighted F1: 0.828
• Macro Precision: 0.828
• Micro Precision: 0.828
• Weighted Precision: 0.828
• Macro Recall: 0.828
• Micro Recall: 0.828
• Weighted Recall: 0.828