Machine learning predictive models of likelihood of bot types given speech topics
| Direction of relationship with bot likelihood (+/−) | ||||||
|---|---|---|---|---|---|---|
| All bots | Astroturf | Fake follower | Financial | Self-declared | Spammer | |
| Topic 8 | – | – | – | + | – | – |
| Topic 17 | – | – | – | + | – | – |
| Topic 4 | – | – | – | – | – | – |
| Topic 18 | + | + | + | – | + | – |
| Topic 1 | + | – | – | – | + | + |
| Topic 12 | – | – | – | – | – | – |
| Topic 3 | + | – | – | – | + | + |
| Topic 21 | – | – | – | – | – | – |
| Topic 6 | + | + | – | – | – | – |
| Topic 23 | – | + | – | – | – | – |
| Topic 19 | – | + | + | – | – | – |
| Topic 13 | + | + | + | – | – | + |
| Topic 7 | – | + | – | + | – | + |
| Topic 24 | + | – | – | – | – | – |
| Topic 9 | + | – | – | – | + | – |
| Topic 14 | + | – | + | – | + | – |
| Topic 22 | – | + | – | – | – | – |
| Topic 10 | + | – | – | – | – | – |
| Topic 11 | + | + | – | – | + | – |
| Topic 16 | + | + | + | – | + | – |
| Topic 15 | + | + | – | – | + | – |
| Topic 20 | + | – | – | – | + | – |
| Topic 5 | + | – | – | – | + | – |
| Topic 2 | – | – | – | – | – | – |
| Topic 25 | – | – | – | + | – | – |
| N | 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 |
| Model accuracy | 86.16% | 99.01% | 99.44% | 99.97% | 90.64% | 99.09% |
| Direction of relationship with bot likelihood (+/−) | ||||||
|---|---|---|---|---|---|---|
| All bots | Astroturf | Fake follower | Financial | Self-declared | Spammer | |
| Topic 8 | – | – | – | + | – | – |
| Topic 17 | – | – | – | + | – | – |
| Topic 4 | – | – | – | – | – | – |
| Topic 18 | + | + | + | – | + | – |
| Topic 1 | + | – | – | – | + | + |
| Topic 12 | – | – | – | – | – | – |
| Topic 3 | + | – | – | – | + | + |
| Topic 21 | – | – | – | – | – | – |
| Topic 6 | + | + | – | – | – | – |
| Topic 23 | – | + | – | – | – | – |
| Topic 19 | – | + | + | – | – | – |
| Topic 13 | + | + | + | – | – | + |
| Topic 7 | – | + | – | + | – | + |
| Topic 24 | + | – | – | – | – | – |
| Topic 9 | + | – | – | – | + | – |
| Topic 14 | + | – | + | – | + | – |
| Topic 22 | – | + | – | – | – | – |
| Topic 10 | + | – | – | – | – | – |
| Topic 11 | + | + | – | – | + | – |
| Topic 16 | + | + | + | – | + | – |
| Topic 15 | + | + | – | – | + | – |
| Topic 20 | + | – | – | – | + | – |
| Topic 5 | + | – | – | – | + | – |
| Topic 2 | – | – | – | – | – | – |
| Topic 25 | – | – | – | + | – | – |
| 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 | 3,978,103 | |
| 86.16% | 99.01% | 99.44% | 99.97% | 90.64% | 99.09% | |
Note(s): Table shows results from an SVM classification model that predicts type of bot (see header row for type tested in each column) based on the speakers' use of the 25 topics. Model Accuracy shows the accuracy of the model in predicting bots on a 20% “hold-out” sample employing 5-fold cross-validation. The Direction of Relationship column shows the positive or negative direction of each topic's association with each bot type (for brevity, the SVM coefficients are omitted from the table). The bot types are derived from the Botometer API (Davis et al., 2016)
Source(s): Authors' own work
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.