FakeNewsNet is a comprehensive fake news benchmark providing full news articles, social context from Twitter, and ground truth labels from fact-checking sites.
What Is FakeNewsNet?
- Components: News content + social engagement + user profiles
- Sources: PolitiFact and GossipCop fact-checks
- Size: 23,000+ articles with Twitter propagation data
- Research Focus: Multi-modal fake news detection
Why FakeNewsNet Matters
Fake news detection requires more than text analysis—propagation patterns, user credibility, and engagement signals provide crucial signals.
<svg viewBox="0 0 368 340" xmlns="http://www.w3.org/2000/svg" style="max-width:100%;height:auto" role="img"><rect x="0" y="0" width="368" height="340" rx="12" fill="#0d1117"/><g font-family="ui-monospace,SFMono-Regular,Menlo,Consolas,"Liberation Mono",monospace" font-size="14"><text xml:space="preserve" x="20" y="31.7"><tspan fill="#c9d1d9">FakeNewsNet Data Structure:</tspan></text><text xml:space="preserve" x="20" y="50.7"><tspan fill="#6e7681">┌─────────────────────────────────────┐</tspan></text><text xml:space="preserve" x="20" y="69.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> News Article </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="88.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Title, body text </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="107.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Source domain </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="126.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Publish date </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="145.7"><tspan fill="#6e7681">├─────────────────────────────────────┤</tspan></text><text xml:space="preserve" x="20" y="164.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> Social Context </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="183.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Tweets sharing article </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="202.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Retweet cascades </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="221.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - User profiles/followers </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="240.7"><tspan fill="#6e7681">├─────────────────────────────────────┤</tspan></text><text xml:space="preserve" x="20" y="259.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> Ground Truth </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="278.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Fact-check verdict </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="297.7"><tspan fill="#6e7681">│</tspan><tspan fill="#c9d1d9"> - Explanation </tspan><tspan fill="#6e7681">│</tspan></text><text xml:space="preserve" x="20" y="316.7"><tspan fill="#6e7681">└─────────────────────────────────────┘</tspan></text></g></svg>
Detection Approaches Using FakeNewsNet:
| Approach | Features | F1 Score |
|---|---|---|
| Text only | Article content | ~70% |
| Social only | Propagation patterns | ~75% |
| Multi-modal | Text + social + user | ~85% |
fakenewsnetmisinformation benchmarksocial media
Explore 500+ Semiconductor & AI Topics
From EUV lithography to CUDA optimization — search the full knowledge base or chat with our AI assistant.