This dataset is the resulting cleaned version of [Panos Kostakos's Risk of being drawn into online sex work](https://www.kaggle.com/panoskostakos/online-sex-work) dataset. Context This database was used in the paper: "Covert online ethnography and machine learning for detecting individuals at risk of being drawn into online sex work". [https://www.flinders.edu.au/centre-crime-policy-research/illicit-networks-workshop](https://www.flinders.edu.au/centre-crime-policy-research/illicit-networks-workshop) Content The database includes data scraped from a European online adult forum. Using covert online ethnography we interviewed a small number of participants and determined their risk to either supply or demand sex services through that forum. This is a great dataset for semi-supervised learning. Acknowledgements The dataset was initially publicized by [Panos Kostakos](https://www.kaggle.com/panoskostakos). Inspiration How can we identify individuals at risk of being drawn into online sex work? The spread of online social media enables a greater number of people to be involved into online sex trade; however, detecting deviant behaviors online is limited by the low available of data. To overcome this challenge, we combine covert online ethnography with semi-supervised learning using data from a popular European adult forum.