Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Three key issues to be addressed.

More »

Fig 1 Expand

Fig 2.

Overview of the proposed NeighborSense framework.

More »

Fig 2 Expand

Fig 3.

The NeighborSense layer with the adaptive gating module.

The dashed box illustrates how the gate zi,r is computed from neighborhood statistics and used to control relation-wise aggregation.

More »

Fig 3 Expand

Table 1.

Dataset statistics.

More »

Table 1 Expand

Table 2.

Relations between users extracted from Twibot-22.

More »

Table 2 Expand

Table 3.

Parameter settings.

More »

Table 3 Expand

Table 4.

Benchmarking results of bot detection approaches.

More »

Table 4 Expand

Fig 4.

Model Scale vs. Detection accuracy.

More »

Fig 4 Expand

Fig 5.

Model performance with training data proportion ranging from 10% to 70% of the whole dataset.

More »

Fig 5 Expand

Fig 6.

Distribution of zi,r for different relations.

More »

Fig 6 Expand

Fig 7.

Visualization of human and bot representations on Twibot-20 via t-SNE 2-D projections.

More »

Fig 7 Expand