Hyperpartisan scorer

This service attempts to classify whether a text is hyper-partisan or not. Our approach, using an ensemble of trained neural networks, is described in a blogpost. Our approach was an entrant in the Sem Eval 2019 Hyperpartisan News Detection Task, where we achieved 82.2% accuracy, winning first prize!

Default annotations
:hyperpartisan Annotation spanning the whole text with the feature "hyperpartisan_probability" (a decimal fraction between 0 and 1).
600 free requests / day
Batch processing not available

Use this pipeline

Single documents

You can process up to 600 documents per day free of charge using the REST API, at an average rate of 2 documents/sec. Higher quotas are available for research users by arrangement, contact us for details.

The API endpoint for this pipeline is:


Create API Key