Largely an unsupervised learning problem, since there are very few labelled datasets for supervised learning approach. The unsupervised approach largely takes the problem as an anomaly detection task wherein documents deviating from the general character are labelled as fake, inculcating a general assumption that most of the news are not fake.
-
Notifications
You must be signed in to change notification settings - Fork 3
abdullahkhilji/Fake-News-Detection
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Used BERT embeddings on LIAR dataset for multi-class classification to achieve state-of-the-art results.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published