@inproceedings{Gossen:2016:AWA:2908131.2908175,
  abstract = {Web archives capture the history of the Web and are therefore an important source to study how societal developments have been reflected on the Web. However, the large size of Web archives and their temporal nature pose many challenges to researchers interested in working with these collections. In this work, we describe the challenges of working with Web archives and propose the research methodology of extracting and studying sub-collections of the archive focused on specific topics and events. We discuss the opportunities and challenges of this approach and suggest a framework for creating sub-collections.},
  acmid = {2908175},
  added-at = {2016-06-06T18:04:25.000+0200},
  address = {New York, NY, USA},
  author = {Gossen, Gerhard and Demidova, Elena and Risse, Thomas},
  biburl = {https://www.bibsonomy.org/bibtex/2a92806dc0205868031b4a89bda5ba6b7/trisse69},
  booktitle = {Proceedings of the 8th ACM Conference on Web Science},
  doi = {10.1145/2908131.2908175},
  interhash = {66d4836e8ca359533e133531e1398f22},
  intrahash = {a92806dc0205868031b4a89bda5ba6b7},
  isbn = {978-1-4503-4208-7},
  keywords = {alexandria myown webarchiving webcrawler},
  location = {Hannover, Germany},
  numpages = {5},
  pages = {291--295},
  publisher = {ACM},
  series = {WebSci '16},
  timestamp = {2017-04-11T15:42:13.000+0200},
  title = {Analyzing Web Archives Through Topic and Event Focused Sub-collections},
  url = {https://arxiv.org/abs/1612.05413},
  year = 2016
}