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

Table 1.

COVID-19 disinformation category data structure.

More »

Table 1 Expand

Table 2.

Label counts and annotation agreements of unfiltered annotation (All) and filtered annotation (Cleaned).

More »

Table 2 Expand

Table 3.

Number of examples per category in the final dataset.

More »

Table 3 Expand

Fig 1.

Overview of model architecture, linear block is the linear transformation (i.e. linear(x) = Wx + b), nonLin is linear transformation with non-linear activation function f(linear(.)), softmax is softmax activated linear function.

More »

Fig 1 Expand

Table 4.

Five-fold cross-valuation classification and topic modelling results, n/a stands for not applicable for the model.

The standard deviation is shown in parentheses. The majority class is ‘PubAuth’ at 19.4%.

More »

Table 4 Expand

Table 5.

COVID-19 disinformation class level F1 score, standard deviation in parentheses.

More »

Table 5 Expand

Fig 2.

a. Percentage stacked column chart of CANTM category prediction b. Percentage stacked column chart of human agreements in the pairwise agreement measurement.

More »

Fig 2 Expand

Table 6.

Statistics of debunked COVID-19 disinformation by IFCN members.

(1 January—30 June 2020).

More »

Table 6 Expand

Fig 3.

Weekly trends of normalised IFCN debunks, COVID related Google searches and categories.

More »

Fig 3 Expand

Fig 4.

Percentage stacked column chart of media type vs. category.

More »

Fig 4 Expand

Fig 5.

Percentage stacked column chart of claim origin vs. category.

More »

Fig 5 Expand

Fig 6.

Percentage stacked column chart of veracity type vs. category.

More »

Fig 6 Expand

Table 7.

COVID-19 classification-associated topics from unlabelled data.

More »

Table 7 Expand