@electronic{cnets.indiana.edu,
   title       = {Click Dataset | Center for Complex Networks and Systems Research}, 
   url         = {http://cnets.indiana.edu/groups/nan/webtraffic/click-dataset/},
   biburl      = {https://puma.uni-kassel.de/url/423a283498289c855a2717f66a454247/hotho},
   keywords    = {click dataset indiana stream traffic web},
   added-at    = {2015-03-24T13:38:36.000+0100},
   description = {},
   interhash   = {423a283498289c855a2717f66a454247}, 
   intrahash   = {423a283498289c855a2717f66a454247}
}

@electronic{webdatacommons.org,
   title       = {WDC - Hyperlink Graph}, 
   url         = {http://webdatacommons.org/hyperlinkgraph/},
   biburl      = {https://puma.uni-kassel.de/url/0086d4201eb0d279e10a98a39503e9b2/hotho},
   keywords    = {dataset graph hyperlink web},
   added-at    = {2013-11-13T10:36:31.000+0100},
   description = {This page provides a large hyperlink graph for public download. The graph has been extracted from the Common Crawl 2012 web corpus and covers 3.5 billion web pages and 128 billion hyperlinks between these pages. To the best of our knowledge, this graph is the largest hyperlink graph that is available to the public outside companies such as Google, Yahoo, and Microsoft. Below we provide instructions on how to download the graph as well as basic statistics about its topology. },
   interhash   = {0086d4201eb0d279e10a98a39503e9b2}, 
   intrahash   = {0086d4201eb0d279e10a98a39503e9b2}
}

@electronic{www.semantic-web-journal.net,
   title       = {A Linked-Data-driven and Semantically-enabled Journal Portal for Scientometrics | www.semantic-web-journal.net}, 
   url         = {http://www.semantic-web-journal.net/blog/linked-data-driven-and-semantically-enabled-journal-portal-scientometrics},
   biburl      = {https://puma.uni-kassel.de/url/7ac56d382af666ef4042fec630aa39f3/hotho},
   keywords    = {data dataset journal linked paper semantic statistics web},
   added-at    = {2013-10-24T09:29:37.000+0200},
   description = {},
   interhash   = {7ac56d382af666ef4042fec630aa39f3}, 
   intrahash   = {7ac56d382af666ef4042fec630aa39f3}
}

@electronic{icwsm.cs.mcgill.ca,
   title       = {ICWSM Datasets}, 
   url         = {http://icwsm.cs.mcgill.ca/},
   biburl      = {https://puma.uni-kassel.de/url/aa721ac5890b1453455c7cfb60786e39/hotho},
   keywords    = {dataset social web},
   added-at    = {2012-09-27T12:05:25.000+0200},
   description = {},
   interhash   = {aa721ac5890b1453455c7cfb60786e39}, 
   intrahash   = {aa721ac5890b1453455c7cfb60786e39}
}

@electronic{www.commoncrawl.org,
   title       = {Accessing the Data | CommonCrawl}, 
   url         = {http://www.commoncrawl.org/data/accessing-the-data/},
   biburl      = {https://puma.uni-kassel.de/url/770c120cddae8e771b16c587ff1253fb/hotho},
   keywords    = {accessing commoncrawl data web dataset},
   added-at    = {2011-11-08T15:53:16.000+0100},
   description = {},
   interhash   = {770c120cddae8e771b16c587ff1253fb}, 
   intrahash   = {770c120cddae8e771b16c587ff1253fb}
}

@electronic{www.theregister.co.uk,
   title       = {Army of 'socialbots' steal gigabytes of Facebook user data}, 
   url         = {http://www.theregister.co.uk/2011/11/01/facebook_infiltration_bots/},
   biburl      = {https://puma.uni-kassel.de/url/9d92347be27b7c84c767199400bb5322/hotho},
   keywords    = {data dataset facebook science social web},
   added-at    = {2011-11-02T13:17:09.000+0100},
   description = {},
   interhash   = {9d92347be27b7c84c767199400bb5322}, 
   intrahash   = {9d92347be27b7c84c767199400bb5322}
}

@electronic{webscope.sandbox.yahoo.com,
   title       = {Webscope from Yahoo! Labs}, 
   url         = {http://webscope.sandbox.yahoo.com/catalog.php},
   biburl      = {https://puma.uni-kassel.de/url/d9da5f26b324d77524cf2bc5716c04a7/hotho},
   keywords    = {language search web dataset},
   added-at    = {2011-10-04T17:49:26.000+0200},
   description = {},
   interhash   = {d9da5f26b324d77524cf2bc5716c04a7}, 
   intrahash   = {d9da5f26b324d77524cf2bc5716c04a7}
}

@electronic{d8taplex.com,
   title       = {d8taplex}, 
   url         = {http://d8taplex.com/},
   biburl      = {https://puma.uni-kassel.de/url/9eb6a8822bb92c8b8927be72ef87b847/hotho},
   keywords    = {data dataset discovery exploration visualization web},
   added-at    = {2011-05-03T10:18:57.000+0200},
   description = {d8taplex helps you discover, visualize and explore data found on the web including time series data},
   interhash   = {9eb6a8822bb92c8b8927be72ef87b847}, 
   intrahash   = {9eb6a8822bb92c8b8927be72ef87b847}
}

@electronic{boston.lti.cs.cmu.edu,
   title       = {The ClueWeb09 Dataset}, 
   url         = {http://boston.lti.cs.cmu.edu/Data/clueweb09/},
   biburl      = {https://puma.uni-kassel.de/url/e72d177444d58aa6b449daecdc8fa659/benz},
   keywords    = {clueweb dataset research web},
   added-at    = {2011-02-04T16:06:58.000+0100},
   description = {},
   interhash   = {e72d177444d58aa6b449daecdc8fa659}, 
   intrahash   = {e72d177444d58aa6b449daecdc8fa659}
}

@electronic{ckan.net,
   title       = {Home - CKAN}, 
   url         = {http://ckan.net/},
   biburl      = {https://puma.uni-kassel.de/url/e683597e86fbdaea53c2b6f4bd808af5/hotho},
   keywords    = {dataset lod register semantic web},
   added-at    = {2010-10-21T20:54:54.000+0200},
   description = {},
   interhash   = {e683597e86fbdaea53c2b6f4bd808af5}, 
   intrahash   = {e683597e86fbdaea53c2b6f4bd808af5}
}

@electronic{richard.cyganiak.de,
   title       = {The Linking Open Data cloud diagram}, 
   url         = {http://richard.cyganiak.de/2007/10/lod/},
   biburl      = {https://puma.uni-kassel.de/url/71f9b4c0a3e288376c9fc02ac7636135/hotho},
   keywords    = {cloud dataset linked open semantic web},
   added-at    = {2010-09-23T09:46:08.000+0200},
   description = {},
   interhash   = {71f9b4c0a3e288376c9fc02ac7636135}, 
   intrahash   = {71f9b4c0a3e288376c9fc02ac7636135}
}

@electronic{km.aifb.kit.edu,
   title       = {Billion Triple Challenge 2010 Dataset}, 
   url         = {http://km.aifb.kit.edu/projects/btc-2010/},
   biburl      = {https://puma.uni-kassel.de/url/0bd6afefa4fa9b8deb385d518ea6d32f/hotho},
   keywords    = {2010 billion challenge dataset semantic triple web},
   added-at    = {2010-07-29T23:05:09.000+0200},
   description = {},
   interhash   = {0bd6afefa4fa9b8deb385d518ea6d32f}, 
   intrahash   = {0bd6afefa4fa9b8deb385d518ea6d32f}
}

@electronic{boston.lti.cs.cmu.edu,
   title       = {The ClueWeb09 Dataset}, 
   url         = {http://boston.lti.cs.cmu.edu/Data/clueweb09/},
   biburl      = {https://puma.uni-kassel.de/url/e72d177444d58aa6b449daecdc8fa659/hotho},
   keywords    = {clueweb09 dataset web},
   added-at    = {2009-07-03T09:29:44.000+0200},
   description = {},
   interhash   = {e72d177444d58aa6b449daecdc8fa659}, 
   intrahash   = {e72d177444d58aa6b449daecdc8fa659}
}

@electronic{www.icwsm.org,
   title       = {ICWSM 2009 - International AAAI Conference on Weblogs and Social Media}, 
   url         = {http://www.icwsm.org/2009/data/},
   biburl      = {https://puma.uni-kassel.de/url/16c1f16853c9fdf2727ba9210a703407/hotho},
   keywords    = {2009 blog challenge conference data dataset social web},
   added-at    = {2008-10-23T20:45:36.000+0200},
   description = {},
   interhash   = {16c1f16853c9fdf2727ba9210a703407}, 
   intrahash   = {16c1f16853c9fdf2727ba9210a703407}
}

@electronic{affsys.com,
   title       = {Web Community Dataset}, 
   url         = {http://affsys.com/experiments/HT2008/},
   biburl      = {https://puma.uni-kassel.de/url/818268fe521d4811ddce8bca088d12de/hotho},
   keywords    = {community dataset ht08 hypertext08 web},
   added-at    = {2008-06-21T20:33:47.000+0200},
   description = {},
   interhash   = {818268fe521d4811ddce8bca088d12de}, 
   intrahash   = {818268fe521d4811ddce8bca088d12de}
}

@electronic{www.uoguelph.ca,
   title       = {The QWS Dataset}, 
   url         = {http://www.uoguelph.ca/~qmahmoud/qws/},
   biburl      = {https://puma.uni-kassel.de/url/bb02be875949567e4a0a84a5aaf4cd8d/hotho},
   keywords    = {answer dataset question semantic service web},
   added-at    = {2007-12-07T21:02:40.000+0100},
   description = {},
   interhash   = {bb02be875949567e4a0a84a5aaf4cd8d}, 
   intrahash   = {bb02be875949567e4a0a84a5aaf4cd8d}
}

@electronic{cs.stanford.edu,
   title       = {Stanford Computer Science}, 
   url         = {http://cs.stanford.edu/research/project.php?id=121},
   biburl      = {https://puma.uni-kassel.de/url/cc09b564b503d02033e8265e84f842f3/hotho},
   keywords    = {crawl dataset web},
   added-at    = {2007-07-19T01:31:59.000+0200},
   description = {},
   interhash   = {cc09b564b503d02033e8265e84f842f3}, 
   intrahash   = {cc09b564b503d02033e8265e84f842f3}
}

@electronic{wing.comp.nus.edu.sg,
   title       = {Web Information Retrieval / Natural Language Processing Group (WING) - NLP/IR resource page on aye}, 
   url         = {http://wing.comp.nus.edu.sg/portal/RPNLPIR/},
   biburl      = {https://puma.uni-kassel.de/url/7478a5e39bf8ea1c6e0a65105f8fd7d3/hotho},
   keywords    = {dataset information ir nlp resource retrieval web},
   added-at    = {2007-03-23T15:16:48.000+0100},
   description = {},
   interhash   = {7478a5e39bf8ea1c6e0a65105f8fd7d3}, 
   intrahash   = {7478a5e39bf8ea1c6e0a65105f8fd7d3}
}