@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{reality.media.mit.edu,
   title       = {MIT Media Lab: Reality Mining}, 
   url         = {http://reality.media.mit.edu/},
   biburl      = {https://puma.uni-kassel.de/url/365294ebae4828f93aca9d32ab116908/hotho},
   keywords    = {data dm everyaware lab media mining reality traces dataset},
   added-at    = {2011-09-30T08:49:38.000+0200},
   description = {},
   interhash   = {365294ebae4828f93aca9d32ab116908}, 
   intrahash   = {365294ebae4828f93aca9d32ab116908}
}

@electronic{arnetminer.org,
   title       = {Citation Network Dataset}, 
   url         = {http://arnetminer.org/citation},
   biburl      = {https://puma.uni-kassel.de/url/e161aac032d6db0c923066015bb6a147/stephandoerfel},
   keywords    = {arnetminer citation dataset},
   added-at    = {2011-09-15T15:22:45.000+0200},
   description = {},
   interhash   = {e161aac032d6db0c923066015bb6a147}, 
   intrahash   = {e161aac032d6db0c923066015bb6a147}
}

@electronic{www.prosper.com,
   title       = {Academics - Prosper}, 
   url         = {http://www.prosper.com/about/academics.aspx},
   biburl      = {https://puma.uni-kassel.de/url/32ce80d74cdbad83e6aeced721034f28/hotho},
   keywords    = {data dataset research},
   added-at    = {2011-09-05T17:04:47.000+0200},
   description = {If you are interested in doing research on Prosper or using Prosper data in support of your research, please contact us.},
   interhash   = {32ce80d74cdbad83e6aeced721034f28}, 
   intrahash   = {32ce80d74cdbad83e6aeced721034f28}
}

@electronic{trec.nist.gov,
   title       = {Tweets2011 Twitter Collection}, 
   url         = {http://trec.nist.gov/data/tweets/},
   biburl      = {https://puma.uni-kassel.de/url/6114f26ca8c1a62f39518e1eadc722bc/hotho},
   keywords    = {corpus dataset everyaware twitter},
   added-at    = {2011-09-02T10:41:42.000+0200},
   description = {Tweets2011  As part of the TREC 2011 microblog track, Twitter provided identifiers for approximately 16 million tweets sampled between January 23rd and February 8th, 2011. The corpus is designed to be a reusable, representative sample of the twittersphere - i.e. both important and spam tweets are included.},
   interhash   = {6114f26ca8c1a62f39518e1eadc722bc}, 
   intrahash   = {6114f26ca8c1a62f39518e1eadc722bc}
}

@electronic{code.richrelevance.com,
   title       = {RecLab Core -}, 
   url         = {http://code.richrelevance.com/reclab-core/},
   biburl      = {https://puma.uni-kassel.de/url/e9702e7751ffd591cca67add470d3f6b/hotho},
   keywords    = {algorithm challenge data dataset development improvement method recommender},
   added-at    = {2011-05-26T11:48:26.000+0200},
   description = {},
   interhash   = {e9702e7751ffd591cca67add470d3f6b}, 
   intrahash   = {e9702e7751ffd591cca67add470d3f6b}
}

@electronic{d8taplex.com,
   title       = {Datasets}, 
   url         = {http://d8taplex.com/directory/directory.html},
   biburl      = {https://puma.uni-kassel.de/url/12f0b282945915b09de3b87be9948ab0/hotho},
   keywords    = {dataset series time},
   added-at    = {2011-05-03T10:19:39.000+0200},
   description = {},
   interhash   = {12f0b282945915b09de3b87be9948ab0}, 
   intrahash   = {12f0b282945915b09de3b87be9948ab0}
}

@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{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/hotho},
   keywords    = {dataset network social twitter},
   added-at    = {2011-03-24T10:18:26.000+0100},
   description = {},
   interhash   = {39fbd40f2a9a8d4682162507b2a41924}, 
   intrahash   = {39fbd40f2a9a8d4682162507b2a41924}
}

@electronic{web-ngram.research.microsoft.com,
   title       = {Microsoft Research - Speller Challenge Datasets}, 
   url         = {http://web-ngram.research.microsoft.com/spellerchallenge/DataSets.aspx},
   biburl      = {https://puma.uni-kassel.de/url/ec1f2805048b9ac374691a1774514620/benz},
   keywords    = {challenge dataset search_engine speller_challenge spelling},
   added-at    = {2011-03-16T23:23:07.000+0100},
   description = {Microsoft Research Speller Challenge},
   interhash   = {ec1f2805048b9ac374691a1774514620}, 
   intrahash   = {ec1f2805048b9ac374691a1774514620}
}

@electronic{pig.apache.org,
   title       = {Welcome to Apache Pig!}, 
   url         = {http://pig.apache.org/},
   biburl      = {https://puma.uni-kassel.de/url/a16819a4998a5d215dd1b28d7ebd6f18/hotho},
   keywords    = {analysis dataset datastore large pig},
   added-at    = {2011-03-14T18:59:41.000+0100},
   description = {},
   interhash   = {a16819a4998a5d215dd1b28d7ebd6f18}, 
   intrahash   = {a16819a4998a5d215dd1b28d7ebd6f18}
}

@electronic{www.pearsonlongman.com,
   title       = {Longman Dictionaries - Dictionaries for Research}, 
   url         = {http://www.pearsonlongman.com/dictionaries/research/dict-research.html},
   biburl      = {https://puma.uni-kassel.de/url/30a773117f918e4d932e0c64e5ec6a38/benz},
   keywords    = {dataset dictionary disambiguation ldoce},
   added-at    = {2011-02-18T23:23:09.000+0100},
   description = {Pearson Longman English Language Teaching (Pearson Longman ELT) is a leading educational publisher of quality resources for all ages and abilities across the curriculum, providing solutions for teachers and students.},
   interhash   = {30a773117f918e4d932e0c64e5ec6a38}, 
   intrahash   = {30a773117f918e4d932e0c64e5ec6a38}
}

@electronic{www.yr-bcn.es,
   title       = {Semantically Annotated Snapshot of the English Wikipedia (SW v.1)}, 
   url         = {http://www.yr-bcn.es/semanticWikipedia},
   biburl      = {https://puma.uni-kassel.de/url/a703bcf3b3890f8a4a61f052228bae8f/benz},
   keywords    = {semantics dataset wikipedia annotated ontology},
   added-at    = {2011-02-04T16:08:40.000+0100},
   description = {},
   interhash   = {a703bcf3b3890f8a4a61f052228bae8f}, 
   intrahash   = {a703bcf3b3890f8a4a61f052228bae8f}
}

@electronic{twapperkeeper.com,
   title       = {Twapper Keeper - Archive Tweets}, 
   url         = {http://twapperkeeper.com/},
   biburl      = {https://puma.uni-kassel.de/url/273e6fdd06c89ce7a09eeb2b1598ee09/benz},
   keywords    = {dataset twapper twapper_keeper twitter},
   added-at    = {2011-02-04T16:07:48.000+0100},
   description = {Allows you to archive and organize your tweets based upon hash tags.},
   interhash   = {273e6fdd06c89ce7a09eeb2b1598ee09}, 
   intrahash   = {273e6fdd06c89ce7a09eeb2b1598ee09}
}

@electronic{www.mail-archive.com,
   title       = {[twitter-dev] Re: Tweet Corpus creation for NLP research}, 
   url         = {http://www.mail-archive.com/twitter-development-talk@googlegroups.com/msg05715.html},
   biburl      = {https://puma.uni-kassel.de/url/1b9716d1f2674e18b3016d3ac6edc16a/benz},
   keywords    = {dataset twitter},
   added-at    = {2011-02-04T16:07:48.000+0100},
   description = {},
   interhash   = {1b9716d1f2674e18b3016d3ac6edc16a}, 
   intrahash   = {1b9716d1f2674e18b3016d3ac6edc16a}
}

@electronic{www.eml-research.de,
   title       = {Download Wikipedia Category Taxonomy}, 
   url         = {http://www.eml-research.de/english/research/nlp/download/wikitaxonomy.php},
   biburl      = {https://puma.uni-kassel.de/url/9d33bae08b8defaa95cda39608876bf6/benz},
   keywords    = {categories category_hierarchy dataset download hierarchy ontology taxonomy wikipedia},
   added-at    = {2011-02-04T16:07:33.000+0100},
   description = {},
   interhash   = {9d33bae08b8defaa95cda39608876bf6}, 
   intrahash   = {9d33bae08b8defaa95cda39608876bf6}
}

@electronic{socialnetworks.mpi-sws.org,
   title       = {Online Social Networks Research @MPI-SWS}, 
   url         = {http://socialnetworks.mpi-sws.org/},
   biburl      = {https://puma.uni-kassel.de/url/bd1d323860ba4faafd18250421c1dc94/benz},
   keywords    = {dataset download misvlove social_network},
   added-at    = {2011-02-04T16:07:28.000+0100},
   description = {},
   interhash   = {bd1d323860ba4faafd18250421c1dc94}, 
   intrahash   = {bd1d323860ba4faafd18250421c1dc94}
}

@electronic{www.p2p.tu-darmstadt.de,
   title       = {Research}, 
   url         = {http://www.p2p.tu-darmstadt.de/research/},
   biburl      = {https://puma.uni-kassel.de/url/f518aee1c775b508e6145577ba08264a/benz},
   keywords    = {dataset social_networks socialnetwork},
   added-at    = {2011-02-04T16:07:27.000+0100},
   description = {},
   interhash   = {f518aee1c775b508e6145577ba08264a}, 
   intrahash   = {f518aee1c775b508e6145577ba08264a}
}

@electronic{evanjones.ca,
   title       = {Extracting Text from Wikipedia}, 
   url         = {http://evanjones.ca/software/wikipedia2text.html},
   biburl      = {https://puma.uni-kassel.de/url/7ee155b9d5b03240e99556cbf828f202/benz},
   keywords    = {data dataset plain_text python text tool wiki wikipedia},
   added-at    = {2011-02-04T16:07:25.000+0100},
   description = {},
   interhash   = {7ee155b9d5b03240e99556cbf828f202}, 
   intrahash   = {7ee155b9d5b03240e99556cbf828f202}
}

@electronic{infochimps.org,
   title       = {Twitter data sets for download - Infochimps}, 
   url         = {http://infochimps.org/tags/twitter},
   biburl      = {https://puma.uni-kassel.de/url/6d90faa71befc28ab285391e88270b86/benz},
   keywords    = {dataset download twitter},
   added-at    = {2011-02-04T16:07:23.000+0100},
   description = {},
   interhash   = {6d90faa71befc28ab285391e88270b86}, 
   intrahash   = {6d90faa71befc28ab285391e88270b86}
}

@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{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{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{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{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{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{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{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{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{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{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{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}
}

@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{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{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{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.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{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{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{semanticmatching.org,
   title       = {Semantic Matching}, 
   url         = {http://semanticmatching.org/},
   biburl      = {https://puma.uni-kassel.de/url/17e6a3c740469b3904d7a3af7ae7e0e1/hotho},
   keywords    = {dataset geonames wordnet},
   added-at    = {2010-08-09T20:31:40.000+0200},
   description = {S-Match is an open source Java framework for semantic matching. It contains semantic matching, minimal semantic matching and structure preserving semantic matching algorithm implementations.},
   interhash   = {17e6a3c740469b3904d7a3af7ae7e0e1}, 
   intrahash   = {17e6a3c740469b3904d7a3af7ae7e0e1}
}

@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{www.angela-bohn.de,
   title       = {Social Network Data}, 
   url         = {http://www.angela-bohn.de/data.html},
   biburl      = {https://puma.uni-kassel.de/url/f12e6a09d67816c3b8cdfcc628488675/hotho},
   keywords    = {sna dataset},
   added-at    = {2010-07-21T17:13:35.000+0200},
   description = {},
   interhash   = {f12e6a09d67816c3b8cdfcc628488675}, 
   intrahash   = {f12e6a09d67816c3b8cdfcc628488675}
}

@electronic{toreopsahl.com,
   title       = {Online Social Network-dataset now available « Tore Opsahl}, 
   url         = {http://toreopsahl.com/2009/11/10/online-social-network-dataset-now-available/},
   biburl      = {https://puma.uni-kassel.de/url/0cad4813daecaac8d0fb52a2151c7b7e/hotho},
   keywords    = {dataset network social},
   added-at    = {2010-04-30T15:43:34.000+0200},
   description = {},
   interhash   = {0cad4813daecaac8d0fb52a2151c7b7e}, 
   intrahash   = {0cad4813daecaac8d0fb52a2151c7b7e}
}

@electronic{snap.stanford.edu,
   title       = {SNAP: Stanford Network Analysis Platform}, 
   url         = {http://snap.stanford.edu/},
   biburl      = {https://puma.uni-kassel.de/url/1ad0395e70d60ffc6c9a15f7a2ee4f9f/hotho},
   keywords    = {analysis dataset network snap software stanford tools},
   added-at    = {2010-04-29T16:44:14.000+0200},
   description = {},
   interhash   = {1ad0395e70d60ffc6c9a15f7a2ee4f9f}, 
   intrahash   = {1ad0395e70d60ffc6c9a15f7a2ee4f9f}
}

@electronic{acl-arc.comp.nus.edu.sg,
   title       = {ACL Anthology Reference Corpus (ACL ARC)}, 
   url         = {http://acl-arc.comp.nus.edu.sg/},
   biburl      = {https://puma.uni-kassel.de/url/02e1b1ee344b89910970681457820bca/hotho},
   keywords    = {acl dataset paper pdf text},
   added-at    = {2010-03-19T10:55:58.000+0100},
   description = {},
   interhash   = {02e1b1ee344b89910970681457820bca}, 
   intrahash   = {02e1b1ee344b89910970681457820bca}
}

@electronic{www.cs.pitt.edu,
   title       = {MPQA Releases}, 
   url         = {http://www.cs.pitt.edu/mpqa/},
   biburl      = {https://puma.uni-kassel.de/url/f1343ddd814a4f0fb5cdb52db55afa0b/hotho},
   keywords    = {corpus dataset mpqa opinion},
   added-at    = {2010-03-17T11:31:14.000+0100},
   description = {},
   interhash   = {f1343ddd814a4f0fb5cdb52db55afa0b}, 
   intrahash   = {f1343ddd814a4f0fb5cdb52db55afa0b}
}

@electronic{www.hbz-nrw.de,
   title       = {hbz — Linked Open Data}, 
   url         = {http://www.hbz-nrw.de/projekte/linked_open_data/},
   biburl      = {https://puma.uni-kassel.de/url/78c48f31ca7baf0361562149d2aee801/hotho},
   keywords    = {bibliothek data dataset library linked open},
   added-at    = {2010-03-16T08:22:23.000+0100},
   description = {},
   interhash   = {78c48f31ca7baf0361562149d2aee801}, 
   intrahash   = {78c48f31ca7baf0361562149d2aee801}
}

@electronic{learningtorankchallenge.yahoo.com,
   title       = {Yahoo! Learning to Rank Challenge -}, 
   url         = {http://learningtorankchallenge.yahoo.com/},
   biburl      = {https://puma.uni-kassel.de/url/728179cb1d8dd713585072bca2d702c4/hotho},
   keywords    = {challenge learning rank search wettbewerb yahoo dataset},
   added-at    = {2010-02-26T13:47:48.000+0100},
   description = {},
   interhash   = {728179cb1d8dd713585072bca2d702c4}, 
   intrahash   = {728179cb1d8dd713585072bca2d702c4}
}

@electronic{de.finance.yahoo.com,
   title       = {Aktienindizes Deutschland | Yahoo! FinanzenI}, 
   url         = {http://de.finance.yahoo.com/m8},
   biburl      = {https://puma.uni-kassel.de/url/e60acc80ac3911ebd65acbed002c47a4/hotho},
   keywords    = {dataset finanz jpp},
   added-at    = {2009-12-21T15:03:20.000+0100},
   description = {},
   interhash   = {e60acc80ac3911ebd65acbed002c47a4}, 
   intrahash   = {e60acc80ac3911ebd65acbed002c47a4}
}

@electronic{www.math-stat.unibe.ch,
   title       = {Universität Bern - Departement Mathematik und Statistik - Datensätze (IMSV)}, 
   url         = {http://www.math-stat.unibe.ch/content/lehrveranstaltungen/skripten_etc/datasets_imsv/index_ger.html},
   biburl      = {https://puma.uni-kassel.de/url/1857f6627ed49852ce15e1fd5b8664b7/hotho},
   keywords    = {dataset jpp},
   added-at    = {2009-12-21T14:53:57.000+0100},
   description = {von US-amerikanischen Ba},
   interhash   = {1857f6627ed49852ce15e1fd5b8664b7}, 
   intrahash   = {1857f6627ed49852ce15e1fd5b8664b7}
}

@electronic{fisher.osu.edu,
   title       = {The Financial Data Finder}, 
   url         = {http://fisher.osu.edu/fin/osudown.htm},
   biburl      = {https://puma.uni-kassel.de/url/879fde5ca020aaba1009899eaf030a9d/hotho},
   keywords    = {dataset jpp stock},
   added-at    = {2009-12-21T14:42:44.000+0100},
   description = {},
   interhash   = {879fde5ca020aaba1009899eaf030a9d}, 
   intrahash   = {879fde5ca020aaba1009899eaf030a9d}
}

@electronic{pages.stern.nyu.edu,
   title       = {Useful Data Sets}, 
   url         = {http://pages.stern.nyu.edu/~adamodar/New_Home_Page/data.html},
   biburl      = {https://puma.uni-kassel.de/url/5bf8c15c6f5505aa1e9d8c677d7b57dd/hotho},
   keywords    = {jpp dataset},
   added-at    = {2009-12-21T14:40:53.000+0100},
   description = {},
   interhash   = {5bf8c15c6f5505aa1e9d8c677d7b57dd}, 
   intrahash   = {5bf8c15c6f5505aa1e9d8c677d7b57dd}
}

@electronic{www.econ.yale.edu,
   title       = {Online Data - Robert Shiller}, 
   url         = {http://www.econ.yale.edu/~shiller/data.htm},
   biburl      = {https://puma.uni-kassel.de/url/00c2b75b24da13d45538ce5ebed494f8/hotho},
   keywords    = {dataset jpp},
   added-at    = {2009-12-21T14:40:43.000+0100},
   description = {},
   interhash   = {00c2b75b24da13d45538ce5ebed494f8}, 
   intrahash   = {00c2b75b24da13d45538ce5ebed494f8}
}

@electronic{kmi.tugraz.at,
   title       = {A List of Social Tagging Datasets Made Available for Research}, 
   url         = {http://kmi.tugraz.at/staff/markus/datasets/},
   biburl      = {https://puma.uni-kassel.de/url/4407f32751c8f04c10fcac2568d0156a/hotho},
   keywords    = {tagging dataset},
   added-at    = {2009-12-10T16:27:55.000+0100},
   description = {},
   interhash   = {4407f32751c8f04c10fcac2568d0156a}, 
   intrahash   = {4407f32751c8f04c10fcac2568d0156a}
}

@electronic{www-personal.umich.edu,
   title       = {Network data}, 
   url         = {http://www-personal.umich.edu/~mejn/netdata/},
   biburl      = {https://puma.uni-kassel.de/url/2064f6c6b3325d4c1c7753ba0ae2c09a/hotho},
   keywords    = {data network research dataset},
   added-at    = {2009-11-05T08:54:11.000+0100},
   description = {},
   interhash   = {2064f6c6b3325d4c1c7753ba0ae2c09a}, 
   intrahash   = {2064f6c6b3325d4c1c7753ba0ae2c09a}
}

@electronic{webscope.sandbox.yahoo.com,
   title       = {Webscope from Yahoo! Labs}, 
   url         = {http://webscope.sandbox.yahoo.com/},
   biburl      = {https://puma.uni-kassel.de/url/5ebfa15a7a6be1c6d97165e009b3a9c4/hotho},
   keywords    = {yahoo dataset},
   added-at    = {2009-10-23T10:00:30.000+0200},
   description = {},
   interhash   = {5ebfa15a7a6be1c6d97165e009b3a9c4}, 
   intrahash   = {5ebfa15a7a6be1c6d97165e009b3a9c4}
}

@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{ml.nec-labs.com,
   title       = {NEC Animal Dataset}, 
   url         = {http://ml.nec-labs.com/download/data/videoembed/},
   biburl      = {https://puma.uni-kassel.de/url/02d2ea0f5ec7d204044817f3f04a4ac5/hotho},
   keywords    = {animal dataset evaluation nec},
   added-at    = {2009-05-17T08:48:16.000+0200},
   description = {},
   interhash   = {02d2ea0f5ec7d204044817f3f04a4ac5}, 
   intrahash   = {02d2ea0f5ec7d204044817f3f04a4ac5}
}

@electronic{www.yr-bcn.es,
   title       = {semantically_annotated_snapshot_of_wikipedia}, 
   url         = {http://www.yr-bcn.es/semanticWikipedia},
   biburl      = {https://puma.uni-kassel.de/url/a703bcf3b3890f8a4a61f052228bae8f/hotho},
   keywords    = {tagging dataset wikipedia semantic pos},
   added-at    = {2009-04-09T10:41:38.000+0200},
   description = {},
   interhash   = {a703bcf3b3890f8a4a61f052228bae8f}, 
   intrahash   = {a703bcf3b3890f8a4a61f052228bae8f}
}

@electronic{givealink.org,
   title       = {Social Spam Detection Benjamin Markines Ciro Cattuto Filippo Menczer}, 
   url         = {http://givealink.org/Site/socialspam.html},
   biburl      = {https://puma.uni-kassel.de/url/5c0a079043ca59026f82d178ffa4e4e6/hotho},
   keywords    = {detection dataset classification bibsonomy spam},
   added-at    = {2009-04-01T17:04:55.000+0200},
   description = {Social Spam Detection},
   interhash   = {5c0a079043ca59026f82d178ffa4e4e6}, 
   intrahash   = {5c0a079043ca59026f82d178ffa4e4e6}
}

@electronic{www.stanford.edu,
   title       = {Yahoo datasets}, 
   url         = {http://www.stanford.edu/class/cs345a/YahooData.pdf},
   biburl      = {https://puma.uni-kassel.de/url/94d629d8703f49eae5b2c248a4cc0c94/hotho},
   keywords    = {dataset yahoo},
   added-at    = {2009-03-13T16:26:34.000+0100},
   description = {},
   interhash   = {94d629d8703f49eae5b2c248a4cc0c94}, 
   intrahash   = {94d629d8703f49eae5b2c248a4cc0c94}
}

@electronic{cophir.isti.cnr.it,
   title       = {CoPhIR - COntent-based Photo Image Retrieval}, 
   url         = {http://cophir.isti.cnr.it/},
   biburl      = {https://puma.uni-kassel.de/url/88e726508b341bdda12ae47eddec5c9f/hotho},
   keywords    = {audio dataset flickr ir multimedia search similarity},
   added-at    = {2009-03-03T15:25:25.000+0100},
   description = {},
   interhash   = {88e726508b341bdda12ae47eddec5c9f}, 
   intrahash   = {88e726508b341bdda12ae47eddec5c9f}
}

@electronic{cyber.law.harvard.edu,
   title       = {Tastes, Ties, and Time: Facebook data release | Berkman Center}, 
   url         = {http://cyber.law.harvard.edu/node/4682},
   biburl      = {https://puma.uni-kassel.de/url/1a39b0ec73dcaaefe387dc0a1b5b1016/hotho},
   keywords    = {Facebook dataset},
   added-at    = {2009-01-29T15:46:42.000+0100},
   description = {llaboration with Harvard sociology graduate stu},
   interhash   = {1a39b0ec73dcaaefe387dc0a1b5b1016}, 
   intrahash   = {1a39b0ec73dcaaefe387dc0a1b5b1016}
}

@electronic{ict.ewi.tudelft.nl,
   title       = {ICT - Information and Communication Theory Group}, 
   url         = {http://ict.ewi.tudelft.nl/index.php?option=com_sections&id=178&Itemid=328},
   biburl      = {https://puma.uni-kassel.de/url/890b71b8e5e266184b294d84d84b6b3a/hotho},
   keywords    = {dataset folksonomy librarything tagging},
   added-at    = {2009-01-19T21:22:47.000+0100},
   description = {},
   interhash   = {890b71b8e5e266184b294d84d84b6b3a}, 
   intrahash   = {890b71b8e5e266184b294d84d84b6b3a}
}

@electronic{aws.amazon.com,
   title       = {Public Data Sets on Amazon Web Services (AWS)}, 
   url         = {http://aws.amazon.com/publicdatasets/},
   biburl      = {https://puma.uni-kassel.de/url/5c00bcb3e1a9fef5bac20d557fa32fe8/hotho},
   keywords    = {amazon dataset ontology public},
   added-at    = {2009-01-06T18:07:54.000+0100},
   description = {},
   interhash   = {5c00bcb3e1a9fef5bac20d557fa32fe8}, 
   intrahash   = {5c00bcb3e1a9fef5bac20d557fa32fe8}
}

@electronic{www.bibsonomy.org,
   title       = {BibSonomy::faq}, 
   url         = {http://www.bibsonomy.org/faq#faq-dataset-1},
   biburl      = {https://puma.uni-kassel.de/url/8c0654eb40ba41c344890d373b320157/stumme},
   keywords    = {bibsonomy dataset dump},
   added-at    = {2008-11-28T11:01:10.000+0100},
   description = {},
   interhash   = {8c0654eb40ba41c344890d373b320157}, 
   intrahash   = {8c0654eb40ba41c344890d373b320157}
}

@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{www.kyb.mpg.de,
   title       = {Some code and datasets}, 
   url         = {http://www.kyb.mpg.de/bs/people/pgehler/code/index.html},
   biburl      = {https://puma.uni-kassel.de/url/acd8f53b051daf792deb29f10057e7c4/hotho},
   keywords    = {clustering code matlab plsa dataset},
   added-at    = {2008-10-10T17:20:02.000+0200},
   description = {},
   interhash   = {acd8f53b051daf792deb29f10057e7c4}, 
   intrahash   = {acd8f53b051daf792deb29f10057e7c4}
}

@electronic{www.showusabetterway.co.uk,
   title       = {Show Us a Better Way: What public data is already available?}, 
   url         = {http://www.showusabetterway.co.uk/call/data.html},
   biburl      = {https://puma.uni-kassel.de/url/6e3749725235f376ba16ae7173e038a1/hotho},
   keywords    = {data dataset public},
   added-at    = {2008-07-03T14:42:07.000+0200},
   description = {},
   interhash   = {6e3749725235f376ba16ae7173e038a1}, 
   intrahash   = {6e3749725235f376ba16ae7173e038a1}
}

@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{devoted.to,
   title       = {David Lee's Bookmarks for Corpus-based Linguists}, 
   url         = {http://devoted.to/corpora},
   biburl      = {https://puma.uni-kassel.de/url/714a6270040c564229df5c60db472484/hotho},
   keywords    = {corpus dataset lecture nlp survey},
   added-at    = {2008-04-29T15:03:05.000+0200},
   description = {},
   interhash   = {714a6270040c564229df5c60db472484}, 
   intrahash   = {714a6270040c564229df5c60db472484}
}

@electronic{www.grsampson.net,
   title       = {Geoffrey Sampson: Downloadable Resources}, 
   url         = {http://www.grsampson.net/Resources.html},
   biburl      = {https://puma.uni-kassel.de/url/85e6aa977e160d792141038d38915682/hotho},
   keywords    = {corpus dataset lecture nlp tm},
   added-at    = {2008-04-29T12:09:45.000+0200},
   description = {},
   interhash   = {85e6aa977e160d792141038d38915682}, 
   intrahash   = {85e6aa977e160d792141038d38915682}
}

@electronic{www.linguistlist.org,
   title       = {Linguist List - Web Resource Listings}, 
   url         = {http://www.linguistlist.org/sp/Texts.html},
   biburl      = {https://puma.uni-kassel.de/url/70d16dc2e74cf3bb1f8fe4f8dbd8f17f/hotho},
   keywords    = {corpus dataset lecture nlp},
   added-at    = {2008-04-29T12:06:42.000+0200},
   description = {},
   interhash   = {70d16dc2e74cf3bb1f8fe4f8dbd8f17f}, 
   intrahash   = {70d16dc2e74cf3bb1f8fe4f8dbd8f17f}
}

@electronic{people.csail.mit.edu,
   title       = {Home Page for 20 Newsgroups Data Set}, 
   url         = {http://people.csail.mit.edu/jrennie/20Newsgroups/},
   biburl      = {https://puma.uni-kassel.de/url/bbb84b0f8c4f9921aaa40e1a07190279/hotho},
   keywords    = {20 dataset newsgroups text},
   added-at    = {2008-04-12T15:32:30.000+0200},
   description = {The 20 Newsgroups data set},
   interhash   = {bbb84b0f8c4f9921aaa40e1a07190279}, 
   intrahash   = {bbb84b0f8c4f9921aaa40e1a07190279}
}

@electronic{kdd.ics.uci.edu,
   title       = {20 Newsgroups}, 
   url         = {http://kdd.ics.uci.edu/databases/20newsgroups/20newsgroups.html},
   biburl      = {https://puma.uni-kassel.de/url/6ee032e41e462edbe7baf2db309d0370/hotho},
   keywords    = {20 dataset newsgroups text},
   added-at    = {2008-04-12T15:32:12.000+0200},
   description = {20 Newsgroups 


 Abstract
This data set consists of 20000 messages taken from 20 Usenet newsgroups.

 Information files:


    description of the data 


 Data files:


    20_newsgroups.tar.gz (17.3M; 61.6M uncompressed)
    mini_newsgroups.tar.gz A subset composed of 100 articles from each newsgroup. (1.9M; 6.2M uncompressed)},
   interhash   = {6ee032e41e462edbe7baf2db309d0370}, 
   intrahash   = {6ee032e41e462edbe7baf2db309d0370}
}

@electronic{www.trustlet.org,
   title       = {Trust network datasets - TrustLet}, 
   url         = {http://www.trustlet.org/wiki/Trust_network_datasets},
   biburl      = {https://puma.uni-kassel.de/url/28908984590899659babe3d36cc23a0a/hotho},
   keywords    = {dataset network},
   added-at    = {2008-02-14T09:48:49.000+0100},
   description = {},
   interhash   = {28908984590899659babe3d36cc23a0a}, 
   intrahash   = {28908984590899659babe3d36cc23a0a}
}

@electronic{research.google.com,
   title       = {Google Research Home}, 
   url         = {http://research.google.com/},
   biburl      = {https://puma.uni-kassel.de/url/bc85c9e88e2153ae82d2d0f3be0dc5d5/hotho},
   keywords    = {data dataset google research},
   added-at    = {2008-01-22T10:27:09.000+0100},
   description = {},
   interhash   = {bc85c9e88e2153ae82d2d0f3be0dc5d5}, 
   intrahash   = {bc85c9e88e2153ae82d2d0f3be0dc5d5}
}

@electronic{research.microsoft.com,
   title       = {LETOR: Benchmark Datasets for Learning to Rank}, 
   url         = {http://research.microsoft.com/users/tyliu/LETOR/},
   biburl      = {https://puma.uni-kassel.de/url/69c5ffa9987277d3c2b6a87e8e643c73/hotho},
   keywords    = {benchmark dataset learning microsoft ranking},
   added-at    = {2008-01-01T13:56:17.000+0100},
   description = {},
   interhash   = {69c5ffa9987277d3c2b6a87e8e643c73}, 
   intrahash   = {69c5ffa9987277d3c2b6a87e8e643c73}
}

@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{mlkd.csd.auth.gr,
   title       = {Multilabel Classification}, 
   url         = {http://mlkd.csd.auth.gr/multilabel.html},
   biburl      = {https://puma.uni-kassel.de/url/ca1734ab575c5ca632a28d7b59aa4d5b/hotho},
   keywords    = {classification dataset extension multilabel text tools weka},
   added-at    = {2007-11-23T13:12:59.000+0100},
   description = {Multi-Label Classification},
   interhash   = {ca1734ab575c5ca632a28d7b59aa4d5b}, 
   intrahash   = {ca1734ab575c5ca632a28d7b59aa4d5b}
}

@electronic{aune.lpl.univ-aix.fr,
   title       = {Multext}, 
   url         = {http://aune.lpl.univ-aix.fr/projects/multext/},
   biburl      = {https://puma.uni-kassel.de/url/aadc8b8fde1c4cc4affcfa02f649f6be/hotho},
   keywords    = {corpus dataset text},
   added-at    = {2007-11-16T17:36:20.000+0100},
   description = {},
   interhash   = {aadc8b8fde1c4cc4affcfa02f649f6be}, 
   intrahash   = {aadc8b8fde1c4cc4affcfa02f649f6be}
}

@electronic{www.aifb.uni-karlsruhe.de,
   title       = {Index of /WBS/seb/datasets}, 
   url         = {http://www.aifb.uni-karlsruhe.de/WBS/seb/datasets/},
   biburl      = {https://puma.uni-kassel.de/url/eeaaa900f5fbebb01ebdb65392ec6937/hotho},
   keywords    = {dataset relation},
   added-at    = {2007-09-20T12:10:48.000+0200},
   description = {},
   interhash   = {eeaaa900f5fbebb01ebdb65392ec6937}, 
   intrahash   = {eeaaa900f5fbebb01ebdb65392ec6937}
}

@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{www.yr-bcn.es,
   title       = {Datasets}, 
   url         = {http://www.yr-bcn.es/webspam/datasets/},
   biburl      = {https://puma.uni-kassel.de/url/738cfa05f2740cb277561053597f68e4/hotho},
   keywords    = {dataset detection spam webspam},
   added-at    = {2007-07-19T01:15:17.000+0200},
   description = {},
   interhash   = {738cfa05f2740cb277561053597f68e4}, 
   intrahash   = {738cfa05f2740cb277561053597f68e4}
}

@electronic{www.cs.cmu.edu,
   title       = {Enron Email Dataset}, 
   url         = {http://www.cs.cmu.edu/~enron/},
   biburl      = {https://puma.uni-kassel.de/url/05a1ec4b5e4ce2559c5435b637484ccf/hotho},
   keywords    = {KI2007WebMining dataset email enron},
   added-at    = {2007-05-18T20:38:46.000+0200},
   description = {},
   interhash   = {05a1ec4b5e4ce2559c5435b637484ccf}, 
   intrahash   = {05a1ec4b5e4ce2559c5435b637484ccf}
}

@electronic{www.ecmlpkdd2006.org,
   title       = {ECML/PKDD Discovery Challenge 2006}, 
   url         = {http://www.ecmlpkdd2006.org/challenge.html},
   biburl      = {https://puma.uni-kassel.de/url/1564dc028dc534329f5e50e18d625fba/hotho},
   keywords    = {KI2007WebMining dataset detection email spam},
   added-at    = {2007-05-18T20:38:05.000+0200},
   description = {},
   interhash   = {1564dc028dc534329f5e50e18d625fba}, 
   intrahash   = {1564dc028dc534329f5e50e18d625fba}
}

@electronic{research.microsoft.com,
   title       = {LETOR: Benchmark Data Sets for Learning to Rank}, 
   url         = {http://research.microsoft.com/research/downloads/details/22a1b3e9-c5c6-4cfe-86f9-1d2ea1c199e8/details.aspx},
   biburl      = {https://puma.uni-kassel.de/url/f5674b623e2b474d00e938128f6e9066/hotho},
   keywords    = {benchmark dataset ranking},
   added-at    = {2007-04-17T09:15:32.000+0200},
   description = {},
   interhash   = {f5674b623e2b474d00e938128f6e9066}, 
   intrahash   = {f5674b623e2b474d00e938128f6e9066}
}

@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}
}

@electronic{www.nytimes.com,
   title       = {Researchers Yearn to Use AOL Logs, but They Hesitate - New York Times}, 
   url         = {http://www.nytimes.com/2006/08/23/technology/23search.html?ei=5088&en=cc878412ed34dad0&ex=1313985600&partner=rssnyt&emc=rss&pagewanted=all},
   biburl      = {https://puma.uni-kassel.de/url/e2b38547cec7cb40c42f76b4df686a14/hotho},
   keywords    = {presse dataset aol},
   added-at    = {2007-02-19T12:49:31.000+0100},
   description = {},
   interhash   = {e2b38547cec7cb40c42f76b4df686a14}, 
   intrahash   = {e2b38547cec7cb40c42f76b4df686a14}
}

@electronic{www.cs.cornell.edu,
   title       = {Datasets from transcripts of US Congressional floor debates}, 
   url         = {http://www.cs.cornell.edu/home/llee/data/convote.html},
   biburl      = {https://puma.uni-kassel.de/url/59a77db17bc3f77f9da8b3a7e0824a71/hotho},
   keywords    = {classification dataset text},
   added-at    = {2007-02-06T21:26:30.000+0100},
   description = {Congressional speech data},
   interhash   = {59a77db17bc3f77f9da8b3a7e0824a71}, 
   intrahash   = {59a77db17bc3f77f9da8b3a7e0824a71}
}

@electronic{groups.google.com,
   title       = {comp.lang.perl.modules | Google Groups}, 
   url         = {http://groups.google.com/group/comp.lang.perl.modules/browse_thread/thread/619db8926623c188/dd4500f068555338?lnk=st&q=perl+mysql+large+datasets&rnum=14&hl=en#dd4500f068555338},
   biburl      = {https://puma.uni-kassel.de/url/467965559554e0df63cb83e24b35d490/hotho},
   keywords    = {perl large mysql dataset},
   added-at    = {2007-02-01T10:41:52.000+0100},
   description = {},
   interhash   = {467965559554e0df63cb83e24b35d490}, 
   intrahash   = {467965559554e0df63cb83e24b35d490}
}

@electronic{www.acm.org,
   title       = {ACM SIGKDD: Special Issue on Learning from Inbalanced Datasets}, 
   url         = {http://www.acm.org/sigs/sigkdd/explorations/issue.php?volume=6&issue=1&year=2004&month=06},
   biburl      = {https://puma.uni-kassel.de/url/6b3d48edda0583cf14d2fd48e37d056f/hotho},
   keywords    = {data dataset inbalanced learning svm},
   added-at    = {2007-01-28T16:19:49.000+0100},
   description = {},
   interhash   = {6b3d48edda0583cf14d2fd48e37d056f}, 
   intrahash   = {6b3d48edda0583cf14d2fd48e37d056f}
}

@electronic{vlado.fmf.uni-lj.si,
   title       = {Pajek / How to: Convert text file datasets into Pajek format}, 
   url         = {http://vlado.fmf.uni-lj.si/pub/networks/pajek/howto/text2pajek.htm},
   biburl      = {https://puma.uni-kassel.de/url/500b704755ffeae4cf3108281d02ef36/hotho},
   keywords    = {convert dataset pajek},
   added-at    = {2007-01-26T13:34:34.000+0100},
   description = {},
   interhash   = {500b704755ffeae4cf3108281d02ef36}, 
   intrahash   = {500b704755ffeae4cf3108281d02ef36}
}

@electronic{glaros.dtc.umn.edu,
   title       = {CLUTO - Family of Data Clustering Software Tools | Karypis Lab}, 
   url         = {http://glaros.dtc.umn.edu/gkhome/views/cluto},
   biburl      = {https://puma.uni-kassel.de/url/4c54eae64ee947df3329661b7e520e60/hotho},
   keywords    = {clustering tools dataset dm ml},
   added-at    = {2006-10-25T09:25:47.000+0200},
   description = {},
   interhash   = {4c54eae64ee947df3329661b7e520e60}, 
   intrahash   = {4c54eae64ee947df3329661b7e520e60}
}

@electronic{l2r.cs.uiuc.edu,
   title       = {Learning Question Classifiers}, 
   url         = {http://l2r.cs.uiuc.edu/~cogcomp/Data/QA/QC/},
   biburl      = {https://puma.uni-kassel.de/url/dd876a3d964e592c5eb63738b2e2be77/hotho},
   keywords    = {qa classification dataset},
   added-at    = {2006-10-11T10:27:47.000+0200},
   description = {},
   interhash   = {dd876a3d964e592c5eb63738b2e2be77}, 
   intrahash   = {dd876a3d964e592c5eb63738b2e2be77}
}

@electronic{www.gregsadetsky.com,
   title       = {AOL search data mirrors}, 
   url         = {http://www.gregsadetsky.com/aol-data/},
   biburl      = {https://puma.uni-kassel.de/url/21dc63ef0d343217a90c6dba4f1ad466/hotho},
   keywords    = {search dataset},
   added-at    = {2006-10-07T11:43:25.000+0200},
   description = {This collection consists of ~20M web queries collected from ~650k users over three months.
The data is sorted by anonymous user ID and sequentially arranged.},
   interhash   = {21dc63ef0d343217a90c6dba4f1ad466}, 
   intrahash   = {21dc63ef0d343217a90c6dba4f1ad466}
}

@electronic{www.netflixprize.com,
   title       = {Netflix Prize: Home}, 
   url         = {http://www.netflixprize.com/},
   biburl      = {https://puma.uni-kassel.de/url/716c6bc2bc6446d5eed86227b99903ac/hotho},
   keywords    = {recommender movie dataset preis},
   added-at    = {2006-10-05T22:08:28.000+0200},
   description = {},
   interhash   = {716c6bc2bc6446d5eed86227b99903ac}, 
   intrahash   = {716c6bc2bc6446d5eed86227b99903ac}
}

@electronic{www.site.uottawa.ca,
   title       = {Bibliography}, 
   url         = {http://www.site.uottawa.ca/~nat/Research/class_imbalance_bibli.html},
   biburl      = {https://puma.uni-kassel.de/url/b2564e078b839505e250a23eee287399/hotho},
   keywords    = {data dataset paper imbalance},
   added-at    = {2006-09-19T12:09:43.000+0200},
   description = { Imbalance Problem},
   interhash   = {b2564e078b839505e250a23eee287399}, 
   intrahash   = {b2564e078b839505e250a23eee287399}
}

@electronic{plg.uwaterloo.ca,
   title       = {Trec Spam Corpus}, 
   url         = {http://plg.uwaterloo.ca/~gvcormac/treccorpus/},
   biburl      = {https://puma.uni-kassel.de/url/612bf65a435736bdb79b895c6b070429/hotho},
   keywords    = {trec spam set data dataset corpus},
   added-at    = {2006-09-04T15:42:51.000+0200},
   description = {},
   interhash   = {612bf65a435736bdb79b895c6b070429}, 
   intrahash   = {612bf65a435736bdb79b895c6b070429}
}