Spam Detection Model

Use the default Spam Detection model

Need a general-purpose Spam Detection model? You can use Artifex's default Spam Detection model, which is trained to flag spam messages out-of-the-box:

from artifex import Artifex

spam_detection = Artifex().spam_detection

print(spam_detection("You won an IPhone 16! Click here to claim your prize."))

# >>> [{'label': 'spam', 'score': 0.9999}]

Learn more about the default Spam Detection model and what it considers spam vs non-spam on our Spam Detection HF model page.

Create & use a custom Spam Detection model

Need more control over what is considered spam vs non-spam? Fine-tune your own Spam Detection model, use it locally on CPU and keep it forever:

from artifex import Artifex

spam_detection = Artifex().spam_detection

model_output_path = "./output_model/"

spam_detection.train(
    spam_content=[ # define your own spam content
        "All-caps text.",
        "Limited-time, suspicious offers.",
        "Links to unknown websites.",
        "Requests for personal information.",
    ],
    output_path=model_output_path
)

spam_detection.load(model_output_path)
print(spam_detection("Congratulations! You've won a free vacation to the Bahamas. Click here to claim your prize."))

# >>> [{'label': 'spam', 'score': 0.9970}]