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.

Workflow of the dark web keyword crawler for crime data collection.

More »

Fig 1 Expand

Table 1.

Top 20 keywords extracted using TF-IDF.

More »

Table 1 Expand

Table 2.

Top 20 keywords extracted using eigenvector centrality.

More »

Table 2 Expand

Table 3.

Top 20 keywords extracted using Word2Vec.

More »

Table 3 Expand

Fig 2.

Categorization of the top 20 keywords extracted using individual text mining techniques by crime-related category.

More »

Fig 2 Expand

Table 4.

Validation accuracy based on keywords extracted from individual models.

More »

Table 4 Expand

Table 5.

Top 20 keyword pairs extracted from combined models using eigenvector centrality and TF-IDF.

More »

Table 5 Expand

Table 6.

Top 20 keyword pairs extracted from combined models using eigenvector centrality and Word2Vec.

More »

Table 6 Expand

Fig 3.

Categorization of the top 20 keywords extracted using combined text mining models by crime-related category.

More »

Fig 3 Expand

Table 7.

Validation accuracy based on keyword pairs extracted from combined models.

More »

Table 7 Expand

Table 8.

Multi-seed-based stability verification results for TF-IDF, eigenvector centrality, and Word2Vec models.

More »

Table 8 Expand