Datasets used for training the four given models

BINARY

The Netflix dataset

Trained in movie and TV show reviews posted on Netflix.

The ads HT dataset

Trained in web pages involved in Human Trafficking. Contact mattmann@usc.edu for more information.

CATEGORICAL

The Stanford dataset

Trained in data provided by Stanford University.

The HT ads dataset

Trained in web pages involved in Human Trafficking. Contact mattmann@usc.edu for more information.