Ensemble Sentiment Analysis to Identify Human Trafficking in Web Data

Wemotivate the use of sentiment analysis as a technique for analyzing the presence of human trafficking in escort ads pulled from the open web. Traditional techniques have not focused on sentiment as a textual cue of human trafficking and instead have focused on other visual cues (e.g., presence of tattoos in associated images), or textual cues (specific styles of ad-writing; keywords, etc.). We apply two widely cited sentiment analysis models: the Netflix and Stanford model, and we also train our own binary and categorical (multiclass) sentiment model using escort review data crawled from the open web. The individual model performances and exploratory analysis motivated us to construct two ensemble sentiment models that correctly serve as a feature proxy to identify human trafficking 53% of the time when evaluated against a set of 38,563 ads provided by the DARPA MEMEX project.