Classifying Illegal Advertisements on the Darknet Using NLP

Abstract

The Darknet has become a place to conduct various illegal activities like child labor, contract murder, drug selling while staying anonymous. Traditionally, international and government agencies try to control these activities, but most of those actions are manual and time-consuming. Recently, various researchers developed Machine Learning (ML) approaches trying to aid in the process of detecting illegal activities. The above problem can benefit by using different Natural Language Processing (NLP) techniques. More specifically, researchers have used various classical topic modeling techniques like bag of words, N-grams, Term Frequency, Term Frequency Inverse Document Frequency (TF-IDF) to represent features and train machine learning models. Moreover, researchers have used an imbalanced dataset to perform those experiments. In this work, we use some more modern techniques like Doc2Vec, Bidirectional Encoder Representation From Transformers (BERT) that have not been studied yet. The primary problem of this project is to classify illegal advertisements published on the Darknet by exploring the above-mentioned state of the art and comparing them against known approaches that use classical techniques, like TF-IDF. Also, we use various data balancing techniques and perform experiments using that data on classical techniques like TF-IDF.