Emojis are digital images and icons that are typically used to liven a communication or convey emotion, commonly in texts, tweets and advertisements. In contrast to its use in social media, emoji use in the human trafficking context, especially human trafficking advertisements, is in place of words and as leet characters. In this talk we demonstrate the use of distributional semantic models, in particular Word2Vec, to the emoji space by treating emojis as words. As a result of this translation, we are able to cluster emojis through their use and placement and find a ‘synonym’ list for human trafficking emojis. This work is important as it starts to peel away layers of intended obfuscation in human trafficking communication to help expose trafficker intent and methodology.
LAS aims to bring together a multi-disciplinary group of academic, industry, and government researchers, analysts and managers together to re-engineer the intelligence analysis process to promote predictive analysis. LAS will do this by conducting both classified and unclassified research in a variety of areas of research. The research done in this area will serve as the foundation for mission effects and integrated back into the enterprise.
If you would like to sign up for our email distribution list, please fill out this form: