@electronic{an.kaist.ac.kr,
   title       = {What is Twitter, a Social Network or a News Media? - WWW'10}, 
   url         = {http://an.kaist.ac.kr/traces/WWW2010.html},
   biburl      = {https://puma.uni-kassel.de/url/39fbd40f2a9a8d4682162507b2a41924/benz},
   keywords    = {dataset twitter www www2010},
   added-at    = {2011-02-04T16:07:23.000+0100},
   description = {},
   interhash   = {39fbd40f2a9a8d4682162507b2a41924}, 
   intrahash   = {39fbd40f2a9a8d4682162507b2a41924}
}

@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{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{scientext.msh-alpes.fr,
   title       = {Summary - Scientext}, 
   url         = {http://scientext.msh-alpes.fr/scientext-site-en/spip.php?article1},
   biburl      = {https://puma.uni-kassel.de/url/a903396473ececf187b3bd655b0f5270/benz},
   keywords    = {dataset english french science scientext texts},
   added-at    = {2011-02-04T16:06:37.000+0100},
   description = {Scientext is a new, on-line French and English corpus of scientific texts. The corpus includes 4.8 million running tokens in French, 13 million words of research articles in English (medicine and biology), and an English-language sub-corpus of French undergraduate students’ texts (1,1 million words). The corpus is organized to facilitate the linguistic study of authorial position and reasoning in scientific articles through phraseology and lexico-grammatical markers linked to causality.},
   interhash   = {a903396473ececf187b3bd655b0f5270}, 
   intrahash   = {a903396473ececf187b3bd655b0f5270}
}

@electronic{blog.stackoverflow.com,
   title       = {Stack Overflow Creative Commons Data Dump - Blog – Stack Overflow}, 
   url         = {http://blog.stackoverflow.com/2009/06/stack-overflow-creative-commons-data-dump/},
   biburl      = {https://puma.uni-kassel.de/url/a7fa4f7d006797bc78d35471f0a06c51/benz},
   keywords    = {data dataset stackoverflow},
   added-at    = {2011-02-04T16:06:58.000+0100},
   description = {},
   interhash   = {a7fa4f7d006797bc78d35471f0a06c51}, 
   intrahash   = {a7fa4f7d006797bc78d35471f0a06c51}
}

@electronic{www.springerexemplar.com,
   title       = {Springer Exemplar}, 
   url         = {http://www.springerexemplar.com/},
   biburl      = {https://puma.uni-kassel.de/url/c82d7ad7bd39cf1ca0de43508765b594/hotho},
   keywords    = {dataset extraction springer term},
   added-at    = {2010-10-08T15:15:20.000+0200},
   description = {},
   interhash   = {c82d7ad7bd39cf1ca0de43508765b594}, 
   intrahash   = {c82d7ad7bd39cf1ca0de43508765b594}
}

@electronic{plg1.cs.uwaterloo.ca,
   title       = {Spam Dataset Trec}, 
   url         = {http://plg1.cs.uwaterloo.ca/cgi-bin/cgiwrap/gvcormac/foo07},
   biburl      = {https://puma.uni-kassel.de/url/c61a7a3ad2a1ff12a3967a73a6648972/hotho},
   keywords    = {dataset spam trec},
   added-at    = {2010-08-16T14:03:26.000+0200},
   description = {},
   interhash   = {c61a7a3ad2a1ff12a3967a73a6648972}, 
   intrahash   = {c61a7a3ad2a1ff12a3967a73a6648972}
}

@electronic{plg.uwaterloo.ca,
   title       = {Spam dataset}, 
   url         = {http://plg.uwaterloo.ca/~gvcormac/treccorpus07/},
   biburl      = {https://puma.uni-kassel.de/url/501ec074d8507358fca772f3107e51d2/benz},
   keywords    = {dataset spam},
   added-at    = {2011-02-04T16:07:08.000+0100},
   description = {},
   interhash   = {501ec074d8507358fca772f3107e51d2}, 
   intrahash   = {501ec074d8507358fca772f3107e51d2}
}

@electronic{www.angela-bohn.de,
   title       = {Social Network Data}, 
   url         = {http://www.angela-bohn.de/data.html},
   biburl      = {https://puma.uni-kassel.de/url/f12e6a09d67816c3b8cdfcc628488675/benz},
   keywords    = {data dataset sna social_network},
   added-at    = {2011-02-04T16:07:16.000+0100},
   description = {},
   interhash   = {f12e6a09d67816c3b8cdfcc628488675}, 
   intrahash   = {f12e6a09d67816c3b8cdfcc628488675}
}

@electronic{snap.stanford.edu,
   title       = {SNAP: Network datasets: 476 million Twitter tweets}, 
   url         = {http://snap.stanford.edu/data/twitter7.html},
   biburl      = {https://puma.uni-kassel.de/url/912f04b552308b7b08ec9324848feb56/hotho},
   keywords    = {dataset network twitter},
   added-at    = {2010-12-05T19:59:23.000+0100},
   description = {},
   interhash   = {912f04b552308b7b08ec9324848feb56}, 
   intrahash   = {912f04b552308b7b08ec9324848feb56}
}

@electronic{i.stanford.edu,
   title       = {Mining of Massive Datasets}, 
   url         = {http://i.stanford.edu/~ullman/mmds.html},
   biburl      = {https://puma.uni-kassel.de/url/c126718938b617b07b2c5344a34a2816/benz},
   keywords    = {data data_mining dataset massive},
   added-at    = {2011-02-04T16:06:37.000+0100},
   description = {},
   interhash   = {c126718938b617b07b2c5344a34a2816}, 
   intrahash   = {c126718938b617b07b2c5344a34a2816}
}

@electronic{i.stanford.edu,
   title       = {Mining of Massive Datasets}, 
   url         = {http://i.stanford.edu/~ullman/mmds.html},
   biburl      = {https://puma.uni-kassel.de/url/c126718938b617b07b2c5344a34a2816/hotho},
   keywords    = {book massive mining pdf slides dataset},
   added-at    = {2011-01-24T11:10:59.000+0100},
   description = {},
   interhash   = {c126718938b617b07b2c5344a34a2816}, 
   intrahash   = {c126718938b617b07b2c5344a34a2816}
}

@electronic{dev.mendeley.com,
   title       = {Mendeley's DataTEL Data Set | Mendeley Developers Portal}, 
   url         = {http://dev.mendeley.com/datachallenge/},
   biburl      = {https://puma.uni-kassel.de/url/9624d8840c3535de9328b75e58b98d2b/hotho},
   keywords    = {data dataset datatel mendeley set todo},
   added-at    = {2010-11-14T15:54:58.000+0100},
   description = {Mendeley's DataTEL Data Set},
   interhash   = {9624d8840c3535de9328b75e58b98d2b}, 
   intrahash   = {9624d8840c3535de9328b75e58b98d2b}
}

@electronic{twitter.mpi-sws.org,
   title       = {Measuring User Influence in Twitter}, 
   url         = {http://twitter.mpi-sws.org/},
   biburl      = {https://puma.uni-kassel.de/url/c842973e78f0e46452a21554bc5fa421/hotho},
   keywords    = {dataset paper toread twitter},
   added-at    = {2011-01-03T12:57:32.000+0100},
   description = {},
   interhash   = {c842973e78f0e46452a21554bc5fa421}, 
   intrahash   = {c842973e78f0e46452a21554bc5fa421}
}

@electronic{infochimps.org,
   title       = {Infochimps Data Marketplace / Commons: Download Sell or Share Databases, statistics, data sets for free}, 
   url         = {http://infochimps.org/},
   biburl      = {https://puma.uni-kassel.de/url/f09284bceef641abc13023fb04fe5ddc/benz},
   keywords    = {data dataset datasets download search},
   added-at    = {2011-02-04T16:07:23.000+0100},
   description = {Find and download data in any format, from financial to social networking to GIS data. Or sell data in our data marketplace, at a price you set. We have large data sets, spreadsheets, and databases packed with statistics.},
   interhash   = {f09284bceef641abc13023fb04fe5ddc}, 
   intrahash   = {f09284bceef641abc13023fb04fe5ddc}
}

@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{www.isical.ac.in,
   title       = {Forum for Information Retrieval Evaluation (FIRE)}, 
   url         = {http://www.isical.ac.in/~fire/2010/data_download.html},
   biburl      = {https://puma.uni-kassel.de/url/07a285d731923a9995a4ae69d24dc567/hotho},
   keywords    = {dataset evaluation information retrieval},
   added-at    = {2011-01-07T17:52:13.000+0100},
   description = {},
   interhash   = {07a285d731923a9995a4ae69d24dc567}, 
   intrahash   = {07a285d731923a9995a4ae69d24dc567}
}

@electronic{lshtc.iit.demokritos.gr,
   title       = {Call for Participation | Second Pascal Challenge on Large Scale Hierarchical Text classification}, 
   url         = {http://lshtc.iit.demokritos.gr/},
   biburl      = {https://puma.uni-kassel.de/url/473be765bc5416cd619de9e7ac5e40bf/benz},
   keywords    = {2011 challenge dataset dmoz text_classification wikipedia workshop},
   added-at    = {2011-02-04T16:06:38.000+0100},
   description = {Following a successful first edition, we are pleased to announce the 2nd edition of the Large Scale Hierarchical Text Classification (LSHTC) Pascal Challenge. The LSHTC Challenge is a hierarchical text classification competition, using large datasets. This year’s challenge will increase the scale and the difficulty of the task, using data from Wikipedia (www.wikipedia.org), in addition to the ODP Web directory data (www.dmoz.org).},
   interhash   = {473be765bc5416cd619de9e7ac5e40bf}, 
   intrahash   = {473be765bc5416cd619de9e7ac5e40bf}
}

@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/benz},
   keywords    = {billion_triple data dataset semantic semantic_web},
   added-at    = {2011-02-04T16:07:16.000+0100},
   description = {},
   interhash   = {0bd6afefa4fa9b8deb385d518ea6d32f}, 
   intrahash   = {0bd6afefa4fa9b8deb385d518ea6d32f}
}

@electronic{140kit.com,
   title       = {140kit : The Free, Open Source Twitter Analytics Platform}, 
   url         = {http://140kit.com/},
   biburl      = {https://puma.uni-kassel.de/url/a6d103a457aaa797ece57362215d192a/hotho},
   keywords    = {collection dataset free open toread twitter},
   added-at    = {2011-01-03T13:01:14.000+0100},
   description = {},
   interhash   = {a6d103a457aaa797ece57362215d192a}, 
   intrahash   = {a6d103a457aaa797ece57362215d192a}
}