😡 Emotion Detection model

Use the default Emotion Detection model

Need a general-purpose Emotion Detection model? You can use Artifex's default Emotion Detection model, which is trained to recognize eight emotions out-of-the-box:

• joy
• anger
• fear
• sadness
• surprise
• disgust
• excitement
• neutral

from artifex import Artifex

emotion_detection = Artifex().emotion_detection

print(emotion_detection("I am absolutely thrilled with the results of my project."))

# >>> [{'label': 'excitement', 'score': 0.9916}]

Learn more about the default Emotion Detection model on our Emotion Detection HF model page.

Create & use a custom Emotion Detection model

Need more control over the emotions recognized, or do you want to tailor the model to your specific domain for better results? Fine-tune your own Emotion Detection model, use it locally on CPU and keep it forever:

from artifex import Artifex

emotion_detection = Artifex().emotion_detection

model_output_path = "./output_model/"

emotion_detection.train(
    domain="customer support for an e-commerce platform", # change to your desired domain
    classes={ # define your custom emotions
        "joy": "text that expresses happiness or positivity",
        "anger": "text that expresses anger or frustration",
        "sadness": "text that expresses sadness or sorrow",
        "surprise": "text that expresses surprise or shock",
        "disgust": "text that expresses disgust or revulsion",
        "excitement": "text that expresses excitement or enthusiasm",
        "neutral": "text that either expresses a neutral or indifferent emotion, or that does not express any emotion at all on account of being purely factual or descriptive."
    },
    output_path=model_output_path
)

emotion_detection.load(model_output_path)
print(emotion_detection("This is unacceptable, I want a refund."))

# >>> [{'label': 'anger', 'score': 0.9965}]