@misc{RepkeKrestelEddingetal.2018,
  author    = {Repke, Tim and Krestel, Ralf and Edding, Jakob and Hartmann, Moritz and Hering, Jonas and Kipping, Dennis and Schmidt, Hendrik and Scordialo, Nico and Zenner, Alexander},
  title     = {Beacon in the Dark},
  series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  journal   = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-6014-2},
  doi       = {10.1145/3269206.3269231},
  pages     = {1871 -- 1874},
  year      = {2018},
  abstract  = {The large amount of heterogeneous data in these email corpora renders experts' investigations by hand infeasible. Auditors or journalists, e.g., who are looking for irregular or inappropriate content or suspicious patterns, are in desperate need for computer-aided exploration tools to support their investigations. We present our Beacon system for the exploration of such corpora at different levels of detail. A distributed processing pipeline combines text mining methods and social network analysis to augment the already semi-structured nature of emails. The user interface ties into the resulting cleaned and enriched dataset. For the interface design we identify three objectives expert users have: gain an initial overview of the data to identify leads to investigate, understand the context of the information at hand, and have meaningful filters to iteratively focus onto a subset of emails. To this end we make use of interactive visualisations based on rearranged and aggregated extracted information to reveal salient patterns.},
  language  = {en}
}
@misc{RischKrestel2018,
  author    = {Risch, Julian and Krestel, Ralf},
  title     = {My Approach = Your Apparatus?},
  series = {Libraries},
  journal   = {Libraries},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-5178-2},
  issn      = {2575-7865},
  doi       = {10.1145/3197026.3197038},
  pages     = {283 -- 292},
  year      = {2018},
  abstract  = {Comparative text mining extends from genre analysis and political bias detection to the revelation of cultural and geographic differences, through to the search for prior art across patents and scientific papers. These applications use cross-collection topic modeling for the exploration, clustering, and comparison of large sets of documents, such as digital libraries. However, topic modeling on documents from different collections is challenging because of domain-specific vocabulary. We present a cross-collection topic model combined with automatic domain term extraction and phrase segmentation. This model distinguishes collection-specific and collection-independent words based on information entropy and reveals commonalities and differences of multiple text collections. We evaluate our model on patents, scientific papers, newspaper articles, forum posts, and Wikipedia articles. In comparison to state-of-the-art cross-collection topic modeling, our model achieves up to 13\% higher topic coherence, up to 4\% lower perplexity, and up to 31\% higher document classification accuracy. More importantly, our approach is the first topic model that ensures disjunct general and specific word distributions, resulting in clear-cut topic representations.},
  language  = {en}
}