Table 2 Composition of the US dataset according to domain (mainstream vs disinformation), size class (number of unique users who interact with a given news) and political bias
From: A multi-layer approach to disinformation detection in US and Italian news spreading on Twitter
| Â | No. mainstream | No. disinformation | ||||
|---|---|---|---|---|---|---|
Size class | Left | Right | Tot. | Left | Right | Tot. |
[0,100) | 774 | 2746 | 4177 | 379 | 2086 | 2640 |
[100,1000) | 1712 | 464 | 2605 | 654 | 1946 | 2900 |
[1000,+∞) | 115 | 54 | 196 | 19 | 162 | 235 |
[0,+∞) | 4573 | 1292 | 6978 | 1052 | 4194 | 5575 |