FakeRank
Given a content item, FakeRank returns the probability of that item to be false or misleading.It leverages knowledge from the Web with Deep Learning and Natural Language Processing to understand the meaning of a news story and verify that it is supported by facts.
FakeRank endpoints
| Method | Endpoint | Description |
|---|---|---|
| fakerank | ||
| GET |
classifyProblematicCategory /classify_text |
Returns the identified content category and confidence score in the classification. Return if the content category was identified as problematic |
| GET |
checkToxicScore /toxic_score |
Returns the overall toxicity score and a list of text spans identified as toxic |
| GET |
checkFailedFact /failed_checks |
Returns the identified content category and confidence score in the classification. Return if the content category was identified as problematic |
| GET |
classifySensitiveCategory /classify_sensitive |
Returns further information about the problematic content or empty if it's not suspect |
| GET |
checkFakerankScore /fakerank_score |
The content model considers 10 different signals of Fake News variants including “Pseudo-science”, “Conspiracy”, “Extreme Bias”, “Divisive Language” and more |
FakeRank pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 1 / second |
|