@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{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{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{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{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{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{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{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{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.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{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.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{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{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{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{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{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{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{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{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{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{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{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{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{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{www.sociopatterns.org,
   title       = {DATASETS « SocioPatterns.org}, 
   url         = {http://www.sociopatterns.org/datasets/},
   biburl      = {https://puma.uni-kassel.de/url/870dc1a4d4e6653e5d83183c55eea43e/hotho},
   keywords    = {dynamics patters research rfid socio tags dataset},
   added-at    = {2011-11-04T15:52:12.000+0100},
   description = {A research project that aims to uncover fundamental patterns in social dynamics and coordinated human activity through a data-driven approach.},
   interhash   = {870dc1a4d4e6653e5d83183c55eea43e}, 
   intrahash   = {870dc1a4d4e6653e5d83183c55eea43e}
}

@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{aws.amazon.com,
   title       = {Public Data Sets : Amazon Web Services}, 
   url         = {https://aws.amazon.com/datasets},
   biburl      = {https://puma.uni-kassel.de/url/48b9df49989995b03485eb2292c2c96f/hotho},
   keywords    = {amazon cloud dataset},
   added-at    = {2012-01-25T08:13:17.000+0100},
   description = {},
   interhash   = {48b9df49989995b03485eb2292c2c96f}, 
   intrahash   = {48b9df49989995b03485eb2292c2c96f}
}

@electronic{data.epo.org,
   title       = {EPO -}, 
   url         = {https://data.epo.org/},
   biburl      = {https://puma.uni-kassel.de/url/11a9ffcc313b4cb03e63a50dcbe4dc88/hotho},
   keywords    = {dataset patents},
   added-at    = {2012-04-24T16:00:44.000+0200},
   description = {},
   interhash   = {11a9ffcc313b4cb03e63a50dcbe4dc88}, 
   intrahash   = {11a9ffcc313b4cb03e63a50dcbe4dc88}
}

@electronic{www.kaggle.com,
   title       = {Description - Million Song Dataset Challenge - Kaggle}, 
   url         = {https://www.kaggle.com/c/msdchallenge},
   biburl      = {https://puma.uni-kassel.de/url/4d9684dccd47ad104d5fa19f09837028/hotho},
   keywords    = {categorization dataset million music musik prediction songs},
   added-at    = {2012-04-30T12:57:55.000+0200},
   description = {Kaggle is a platform for data prediction competitions. Companies, organizations and researchers post their data and have it scrutinized by the world's best statisticians.},
   interhash   = {4d9684dccd47ad104d5fa19f09837028}, 
   intrahash   = {4d9684dccd47ad104d5fa19f09837028}
}

@electronic{www.infochimps.com,
   title       = {Million Songs data collection | Infochimps}, 
   url         = {http://www.infochimps.com/collections/million-songs},
   biburl      = {https://puma.uni-kassel.de/url/4e22c4e11eab7d98433f86a4b6922658/hotho},
   keywords    = {dataset download music musik songs},
   added-at    = {2012-04-30T13:51:39.000+0200},
   description = {A collection of 28 datasets containing audio features and metadata for a million contemporary popular music tracks.  The collection represents a collaboration between LabROSA and The Echo Nest. More details, background, and instructions on how to use the datasets can be found at LabROSA’s site. The goal of sharing this data on Infochimps is to provide a large dataset for research and to encourage large-scale algorithms surrounding the data.  There is one dataset for each letter of the alphabet (A-Z) containing data for all songs that start with that letter, one dataset of additional files, and a small sample dataset.  Each of the datasets for each letter consists of song files in the HDF5 format.  Most of the data is licensed the same way as Echo Nest’s API. The code is under GNU public license.},
   interhash   = {4e22c4e11eab7d98433f86a4b6922658}, 
   intrahash   = {4e22c4e11eab7d98433f86a4b6922658}
}

@electronic{opacplus.bib-bvb.de,
   title       = {Online-Hilfe}, 
   url         = {https://opacplus.bib-bvb.de/TouchPoint_touchpoint/help.do?helpContext=opendata},
   biburl      = {https://puma.uni-kassel.de/url/f7036c0c8e8eca12d3f7116f3770af30/hotho},
   keywords    = {bayern dataset katalog online},
   added-at    = {2012-07-15T17:48:06.000+0200},
   description = {},
   interhash   = {f7036c0c8e8eca12d3f7116f3770af30}, 
   intrahash   = {f7036c0c8e8eca12d3f7116f3770af30}
}

@electronic{konect.uni-koblenz.de,
   title       = {KONECT - The Koblenz Network Collection}, 
   url         = {http://konect.uni-koblenz.de/},
   biburl      = {https://puma.uni-kassel.de/url/9db0e03bc323cbbba4199a87ec239bf9/stumme},
   keywords    = {data dataset graphs network networks set},
   added-at    = {2012-08-14T13:40:11.000+0200},
   description = {},
   interhash   = {9db0e03bc323cbbba4199a87ec239bf9}, 
   intrahash   = {9db0e03bc323cbbba4199a87ec239bf9}
}

@electronic{ebiquity.umbc.edu,
   title       = {Google releases dataset linking strings and concepts}, 
   url         = {http://ebiquity.umbc.edu/blogger/2012/05/19/google-releases-database-linking-strings-and-concepts/},
   biburl      = {https://puma.uni-kassel.de/url/a72550cd421df3885e2c4f1ba646f3f6/hotho},
   keywords    = {google linking strings dataset},
   added-at    = {2012-08-20T14:08:46.000+0200},
   description = {},
   interhash   = {a72550cd421df3885e2c4f1ba646f3f6}, 
   intrahash   = {a72550cd421df3885e2c4f1ba646f3f6}
}

@electronic{data.linkedin.com,
   title       = {The LinkedIn Data Team}, 
   url         = {http://data.linkedin.com/},
   biburl      = {https://puma.uni-kassel.de/url/83c7373bc753e40ed7a611b646917cab/hotho},
   keywords    = {data dataset linkedin},
   added-at    = {2012-09-09T16:13:40.000+0200},
   description = {},
   interhash   = {83c7373bc753e40ed7a611b646917cab}, 
   intrahash   = {83c7373bc753e40ed7a611b646917cab}
}

@electronic{konect.uni-koblenz.de,
   title       = {KONECT - The Koblenz Network Collection}, 
   url         = {http://konect.uni-koblenz.de/networks},
   biburl      = {https://puma.uni-kassel.de/url/b013fbde8e7285492579808d2e8102cc/stephandoerfel},
   keywords    = {dataset konect network},
   added-at    = {2012-09-11T17:13:40.000+0200},
   description = {Folksonomy},
   interhash   = {b013fbde8e7285492579808d2e8102cc}, 
   intrahash   = {b013fbde8e7285492579808d2e8102cc}
}

@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{cs.everyaware.eu,
   title       = {Index of /Downloads}, 
   url         = {http://cs.everyaware.eu/datasets/Downloads/?C=M;O=D},
   biburl      = {https://puma.uni-kassel.de/url/b61c3d4de05b0ecc5085d555a3584b69/hotho},
   keywords    = {dataset dump everyaware},
   added-at    = {2012-10-25T14:25:57.000+0200},
   description = {},
   interhash   = {b61c3d4de05b0ecc5085d555a3584b69}, 
   intrahash   = {b61c3d4de05b0ecc5085d555a3584b69}
}

@electronic{data.nytimes.com,
   title       = {New York Times - Linked Open Data}, 
   url         = {http://data.nytimes.com/},
   biburl      = {https://puma.uni-kassel.de/url/4fbecf6bf73ae40fc38b5ad124a8f3ab/hotho},
   keywords    = {data dataset headline linked open subject tags},
   added-at    = {2012-11-13T21:32:46.000+0100},
   description = {},
   interhash   = {4fbecf6bf73ae40fc38b5ad124a8f3ab}, 
   intrahash   = {4fbecf6bf73ae40fc38b5ad124a8f3ab}
}

@electronic{googleresearch.blogspot.de,
   title       = {Learning from Big Data: 40 Million Entities in Context}, 
   url         = {http://googleresearch.blogspot.de/2013/03/learning-from-big-data-40-million.html},
   biburl      = {https://puma.uni-kassel.de/url/14073030361b1ef9cfcc6881845c9a28/hotho},
   keywords    = {40 data dataset learning million wikipedia},
   added-at    = {2013-03-11T09:42:06.000+0100},
   description = {},
   interhash   = {14073030361b1ef9cfcc6881845c9a28}, 
   intrahash   = {14073030361b1ef9cfcc6881845c9a28}
}

@electronic{internetcensus2012.bitbucket.org,
   title       = {Internet Census 2012}, 
   url         = {http://internetcensus2012.bitbucket.org/download.html},
   biburl      = {https://puma.uni-kassel.de/url/08376591f64601b706c6b602e2d24aa5/hotho},
   keywords    = {2012 census internet dataset},
   added-at    = {2013-03-21T17:44:31.000+0100},
   description = {},
   interhash   = {08376591f64601b706c6b602e2d24aa5}, 
   intrahash   = {08376591f64601b706c6b602e2d24aa5}
}

@electronic{www.spiegel.de,
   title       = {Carna-Botnet: Internet-Zensus mit Hacker-Methoden - SPIEGEL ONLINE}, 
   url         = {http://www.spiegel.de/netzwelt/web/carna-botnet-internet-zensus-mit-hacker-methoden-a-890225.html},
   biburl      = {https://puma.uni-kassel.de/url/6a21544c1f679121afd2b52416a22cac/hotho},
   keywords    = {botnet hacker internet zensus dataset},
   added-at    = {2013-03-22T10:19:42.000+0100},
   description = {Wie groß ist das Internet? Ein unbekannter Hacker beantwortet diese Frage jetzt - mit effektiven, aber illegalen Mitteln: Er verschaffte sich Zugriff auf Hunderttausende Router und nutzte sie als Forschungssonde. Das Ergebnis ist ein einzigartiges Abbild des Internets von heute.},
   interhash   = {6a21544c1f679121afd2b52416a22cac}, 
   intrahash   = {6a21544c1f679121afd2b52416a22cac}
}

@electronic{googleresearch.blogspot.de,
   title       = {50,000 Lessons on How to Read: a Relation Extraction Corpus}, 
   url         = {http://googleresearch.blogspot.de/2013/04/50000-lessons-on-how-to-read-relation.html},
   biburl      = {https://puma.uni-kassel.de/url/581c1631a929f1162f86e02337d50478/hotho},
   keywords    = {corpus dataset extraction relation},
   added-at    = {2013-04-17T09:57:10.000+0200},
   description = {},
   interhash   = {581c1631a929f1162f86e02337d50478}, 
   intrahash   = {581c1631a929f1162f86e02337d50478}
}

@electronic{www.csie.ntu.edu.tw,
   title       = {LIBSVM Data: Multi-label Classification}, 
   url         = {http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multilabel.html},
   biburl      = {https://puma.uni-kassel.de/url/a64989029a11e5d34d7df6b38241235d/hotho},
   keywords    = {dataset label libsvm multi reuters},
   added-at    = {2013-04-20T20:27:54.000+0200},
   description = {},
   interhash   = {a64989029a11e5d34d7df6b38241235d}, 
   intrahash   = {a64989029a11e5d34d7df6b38241235d}
}