@article{VoelskeGollubHagenetal.,
  author    = {V{\"o}lske, Michael and Gollub, Tim and Hagen, Matthias and Stein, Benno},
  title     = {A keyquery-based classification system for CORE},
  series = {D-Lib Magazine},
  journal   = {D-Lib Magazine},
  doi       = {10.1045/november14-voelske},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20170426-31662},
  abstract  = {We apply keyquery-based taxonomy composition to compute a classification system for the CORE dataset, a shared crawl of about 850,000 scientific papers. Keyquery-based taxonomy composition can be understood as a two-phase hierarchical document clustering technique that utilizes search queries as cluster labels: In a first phase, the document collection is indexed by a reference search engine, and the documents are tagged with the search queries they are relevant—for their so-called keyqueries. In a second phase, a hierarchical clustering is formed from the keyqueries within an iterative process. We use the explicit topic model ESA as document retrieval model in order to index the CORE dataset in the reference search engine. Under the ESA retrieval model, documents are represented as vectors of similarities to Wikipedia articles; a methodology proven to be advantageous for text categorization tasks. Our paper presents the generated taxonomy and reports on quantitative properties such as document coverage and processing requirements.},
  subject      = {Massendaten},
  language  = {en}
}
@article{VakkariVoelskePotthastetal.,
  author    = {Vakkari, Pertti and V{\"o}lske, Michael and Potthast, Martin and Hagen, Matthias and Stein, Benno},
  title     = {Predicting essay quality from search and writing behavior},
  series = {Journal of Association for Information Science and Technology},
  volume    = {2021},
  journal   = {Journal of Association for Information Science and Technology},
  number    = {volume 72, issue 7},
  publisher = {Wiley},
  address   = {Hoboken, NJ},
  doi       = {10.1002/asi.24451},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210804-44692},
  pages     = {839 -- 852},
  abstract  = {Few studies have investigated how search behavior affects complex writing tasks. We analyze a dataset of 150 long essays whose authors searched the ClueWeb09 corpus for source material, while all querying, clicking, and writing activity was meticulously recorded. We model the effect of search and writing behavior on essay quality using path analysis. Since the boil-down and build-up writing strategies identified in previous research have been found to affect search behavior, we model each writing strategy separately. Our analysis shows that the search process contributes significantly to essay quality through both direct and mediated effects, while the author's writing strategy moderates this relationship. Our models explain 25-35\% of the variation in essay quality through rather simple search and writing process characteristics alone, a fact that has implications on how search engines could personalize result pages for writing tasks. Authors' writing strategies and associated searching patterns differ, producing differences in essay quality. In a nutshell: essay quality improves if search and writing strategies harmonize—build-up writers benefit from focused, in-depth querying, while boil-down writers fare better with a broader and shallower querying strategy.},
  subject      = {Information Retrieval},
  language  = {en}
}
@article{WiegmannKerstenSenaratneetal.,
  author    = {Wiegmann, Matti and Kersten, Jens and Senaratne, Hansi and Potthast, Martin and Klan, Friederike and Stein, Benno},
  title     = {Opportunities and risks of disaster data from social media: a systematic review of incident information},
  series = {Natural Hazards and Earth System Sciences},
  volume    = {2021},
  journal   = {Natural Hazards and Earth System Sciences},
  number    = {Volume 21, Issue 5},
  publisher = {European Geophysical Society},
  address   = {Katlenburg-Lindau},
  doi       = {10.5194/nhess-21-1431-2021},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210804-44634},
  pages     = {1431 -- 1444},
  abstract  = {Compiling and disseminating information about incidents and disasters are key to disaster management and relief. But due to inherent limitations of the acquisition process, the required information is often incomplete or missing altogether. To fill these gaps, citizen observations spread through social media are widely considered to be a promising source of relevant information, and many studies propose new methods to tap this resource. Yet, the overarching question of whether and under which circumstances social media can supply relevant information (both qualitatively and quantitatively) still remains unanswered. To shed some light on this question, we review 37 disaster and incident databases covering 27 incident types, compile a unified overview of the contained data and their collection processes, and identify the missing or incomplete information. The resulting data collection reveals six major use cases for social media analysis in incident data collection: (1) impact assessment and verification of model predictions, (2) narrative generation, (3) recruiting citizen volunteers, (4) supporting weakly institutionalized areas, (5) narrowing surveillance areas, and (6) reporting triggers for periodical surveillance. Furthermore, we discuss the benefits and shortcomings of using social media data for closing information gaps related to incidents and disasters.},
  subject      = {Katastrophe},
  language  = {en}
}