@inproceedings{BuesgenKloeserKohletal.2023,
  author    = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert},
  title     = {From cracked accounts to fake IDs: user profiling on German telegram black market channels},
  series = {Data Management Technologies and Applications},
  booktitle = {Data Management Technologies and Applications},
  editor    = {Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-031-37889-8 (Print)},
  doi       = {10.1007/978-3-031-37890-4_9},
  pages     = {176 -- 202},
  year      = {2023},
  abstract  = {Messenger apps like WhatsApp and Telegram are frequently used for everyday communication, but they can also be utilized as a platform for illegal activity. Telegram allows public groups with up to 200.000 participants. Criminals use these public groups for trading illegal commodities and services, which becomes a concern for law enforcement agencies, who manually monitor suspicious activity in these chat rooms. This research demonstrates how natural language processing (NLP) can assist in analyzing these chat rooms, providing an explorative overview of the domain and facilitating purposeful analyses of user behavior. We provide a publicly available corpus of annotated text messages with entities and relations from four self-proclaimed black market chat rooms. Our pipeline approach aggregates the extracted product attributes from user messages to profiles and uses these with their sold products as features for clustering. The extracted structured information is the foundation for further data exploration, such as identifying the top vendors or fine-granular price analyses. Our evaluation shows that pretrained word vectors perform better for unsupervised clustering than state-of-the-art transformer models, while the latter is still superior for sequence labeling.},
  language  = {en}
}