@electronic{www.coursera.org, title = {Mining Massive Datasets - Stanford University | Coursera}, url = {https://www.coursera.org/course/mmds}, biburl = {https://puma.uni-kassel.de/url/a83f03d8d818f23ff6f40f46a8f18f98/hotho}, keywords = {book buch data dataset massive mining}, added-at = {2015-09-15T14:10:45.000+0200}, description = {Take free online classes from 120+ top universities and educational organizations. We partner with schools like Stanford, Yale, Princeton, and others to offer courses in dozens of topics, from computer science to teaching and beyond. Whether you are pursuing a passion or looking to advance your career, Coursera provides open, free education for everyone.}, interhash = {a83f03d8d818f23ff6f40f46a8f18f98}, intrahash = {a83f03d8d818f23ff6f40f46a8f18f98} } @electronic{academicgraph.blob.core.windows.net, title = {Microsoft Academic Graph}, url = {https://academicgraph.blob.core.windows.net/graph/index.html?eulaaccept=on}, biburl = {https://puma.uni-kassel.de/url/e87433348f8a95093f191b6d916fe82e/hotho}, keywords = {MSAC WSDM challenge citation cup dataset graph}, added-at = {2015-09-15T11:40:16.000+0200}, description = {Microsoft Academic Graph Releases:}, interhash = {e87433348f8a95093f191b6d916fe82e}, intrahash = {e87433348f8a95093f191b6d916fe82e} } @electronic{mcfp.weebly.com, title = {The CTU-13 Dataset. A Labeled Dataset with Botnet, Normal and Background traffic. - Malware Capture  facility project}, url = {http://mcfp.weebly.com/the-ctu-13-dataset-a-labeled-dataset-with-botnet-normal-and-background-traffic.html}, biburl = {https://puma.uni-kassel.de/url/d4dfdd6198cfe22402f9e6599b616499/hotho}, keywords = {WISENT analysis botnet dataset malware project}, added-at = {2015-07-09T16:35:35.000+0200}, description = {}, interhash = {d4dfdd6198cfe22402f9e6599b616499}, intrahash = {d4dfdd6198cfe22402f9e6599b616499} } @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{ewulczyn.github.io, title = {Wikipedia Clickstream - Getting Started – Ellery Wulczyn – Research Analyst at The Wikimedia Foundation}, url = {http://ewulczyn.github.io/Wikipedia_Clickstream_Getting_Started/}, biburl = {https://puma.uni-kassel.de/url/d3111e6af4618baedf03d556572e54d5/hotho}, keywords = {clickstream dataset file log wikipedia}, added-at = {2015-03-09T08:27:02.000+0100}, description = {Research Analyst at The Wikimedia Foundation}, interhash = {d3111e6af4618baedf03d556572e54d5}, intrahash = {d3111e6af4618baedf03d556572e54d5} } @electronic{webscope.sandbox.yahoo.com, title = {Webscope | Yahoo Labs}, url = {http://webscope.sandbox.yahoo.com/catalog.php?datatype=g}, biburl = {https://puma.uni-kassel.de/url/15e6adf9f9ece87a6f79a71fdae1fb46/hotho}, keywords = {dataset labs webscope yahoo}, added-at = {2015-01-15T17:17:26.000+0100}, description = {}, interhash = {15e6adf9f9ece87a6f79a71fdae1fb46}, intrahash = {15e6adf9f9ece87a6f79a71fdae1fb46} } @electronic{fr46.uni-saarland.de, title = {UdS :: FR 4.6:  Register im Kontakt}, url = {http://fr46.uni-saarland.de/index.php?id=regico}, biburl = {https://puma.uni-kassel.de/url/02bd78b005b224e20d38eb8b5c48d359/hotho}, keywords = {corpus dataset hd linguistics}, added-at = {2014-09-29T17:49:06.000+0200}, description = {Universität des Saarlandes,Übersetzung,Dolmetschen,Angewandte Sprachwissenschaft,UdS}, interhash = {02bd78b005b224e20d38eb8b5c48d359}, intrahash = {02bd78b005b224e20d38eb8b5c48d359} } @electronic{www.cs.cmu.edu, title = {Word Similarity Datasets}, url = {http://www.cs.cmu.edu/~mfaruqui/suite.html}, biburl = {https://puma.uni-kassel.de/url/eae19225f318871a9ea8e8b9a6a7a360/hotho}, keywords = {benchmark dataset relations semantic}, added-at = {2014-09-25T16:08:29.000+0200}, description = {Lexical & Distributional Semantics Evaluation Benchmarks}, interhash = {eae19225f318871a9ea8e8b9a6a7a360}, intrahash = {eae19225f318871a9ea8e8b9a6a7a360} } @electronic{alchemy.cs.washington.edu, title = {Alchemy - Open Source AI}, url = {http://alchemy.cs.washington.edu/data/}, biburl = {https://puma.uni-kassel.de/url/7250aee4ca740f486dccc4a5e877d55a/hotho}, keywords = {dataset open source}, added-at = {2014-09-17T12:37:20.000+0200}, description = {}, interhash = {7250aee4ca740f486dccc4a5e877d55a}, intrahash = {7250aee4ca740f486dccc4a5e877d55a} } @electronic{www.stm-assoc.org, title = {Microsoft Word - 2013_11_11_Text_and_Data_Mining_Declaration.doc - 2013_11_11_Text_and_Data_Mining_Declaration.pdf}, url = {http://www.stm-assoc.org/2013_11_11_Text_and_Data_Mining_Declaration.pdf}, biburl = {https://puma.uni-kassel.de/url/332b7f5b1b6633c94bef77be3ccadfa5/hotho}, keywords = {access data dataset journal mining paper sota text}, added-at = {2013-11-27T08:54:41.000+0100}, description = {}, interhash = {332b7f5b1b6633c94bef77be3ccadfa5}, intrahash = {332b7f5b1b6633c94bef77be3ccadfa5} } @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{cnets.indiana.edu, title = {Datasets | Center for Complex Networks and Systems Research}, url = {http://cnets.indiana.edu/groups/nan/webtraffic/websci14-data}, biburl = {https://puma.uni-kassel.de/url/06acbd5c91b36551bb5fda6cb4ebc7ed/hotho}, keywords = {clicklog dataset givealink twitter}, added-at = {2013-11-12T12:58:09.000+0100}, description = {}, interhash = {06acbd5c91b36551bb5fda6cb4ebc7ed}, intrahash = {06acbd5c91b36551bb5fda6cb4ebc7ed} } @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{datamob.org, title = {Datamob: Public data put to good use}, url = {http://datamob.org/}, biburl = {https://puma.uni-kassel.de/url/12210f92620612517f95343c65591cc9/hotho}, keywords = {data dataset public}, added-at = {2013-10-01T14:17:07.000+0200}, description = {Datamob: Public data put to good use.}, interhash = {12210f92620612517f95343c65591cc9}, intrahash = {12210f92620612517f95343c65591cc9} } @electronic{www.lemurproject.org, title = {ClueWeb12 Related Data}, url = {http://www.lemurproject.org/clueweb12.php/related-data.php}, biburl = {https://puma.uni-kassel.de/url/d19569aec60acfdc44a9db0fab914a2f/hotho}, keywords = {2012 clueweb dataset}, added-at = {2013-09-06T09:01:35.000+0200}, description = {The Lemur toolkit for language modeling and information retrieval is documented and made available for download.}, interhash = {d19569aec60acfdc44a9db0fab914a2f}, intrahash = {d19569aec60acfdc44a9db0fab914a2f} } @electronic{lemurproject.org, title = {ClueWeb09 Related Data: FACC1}, url = {http://lemurproject.org/clueweb09/FACC1/}, biburl = {https://puma.uni-kassel.de/url/aea81f94f040659705ae0174074b7785/hotho}, keywords = {annotation clueweb dataset}, added-at = {2013-09-06T08:59:55.000+0200}, description = {Researchers at Google annotated English-language Web pages from the ClueWeb09 and ClueWeb12 corpora. The annotation process was automatic, and hence imperfect. However, the annotations are of generally high quality, as they strove for high precision (and, by necessity, lower recall). For each entity they recognized with high confidence, they provide the beginning and end byte offsets of the entity mention in the input text, its Freebase identifier (mid), and two confidence levels (computed differently, see below). You might consider using this data in conjunction with the recently released Freebase annotations of several TREC query sets. }, interhash = {aea81f94f040659705ae0174074b7785}, intrahash = {aea81f94f040659705ae0174074b7785} } @electronic{www.zubiaga.org, title = {Resources - Arkaitz Zubiaga}, url = {http://www.zubiaga.org/resources/socialbm0311/}, biburl = {https://puma.uni-kassel.de/url/a80c2f0e2d2e1c0336a7d8342197a4df/hotho}, keywords = {dataset delcious}, added-at = {2013-05-16T15:33:50.000+0200}, description = {}, interhash = {a80c2f0e2d2e1c0336a7d8342197a4df}, intrahash = {a80c2f0e2d2e1c0336a7d8342197a4df} } @electronic{leises.berlin.de, title = {Wo ist es laut in Berlin? | Berlin wird leiser}, url = {https://leises.berlin.de/informationen/wo-ist-es-laut-berlin}, biburl = {https://puma.uni-kassel.de/url/4b957195c74918e921fea403ba870aff/hotho}, keywords = {data everyaware lärm noise dataset}, added-at = {2013-05-01T11:09:36.000+0200}, description = {Berlin wird leiser: aktiv gegen Verkehrslärm. - Die Senatsverwaltung für Stadtentwicklung und Umwelt Berlin will ihre Bürger an der Erarbeitung des Lärmaktionsplans beteiligen. Alle Bürgerinnen und Bürger können mitteilen, wo es ihnen in Berlin zu laut ist und welche Maßnahmen Abhilfe schaffen könnten. Auf dieser Basis erarbeitet die Stadt Maßnahmen, wie Berlin leiser werden kann.}, interhash = {4b957195c74918e921fea403ba870aff}, intrahash = {4b957195c74918e921fea403ba870aff} } @electronic{www.cs.cornell.edu, title = {KDD Cup 2003 - Datasets}, url = {http://www.cs.cornell.edu/projects/kddcup/datasets.html}, biburl = {https://puma.uni-kassel.de/url/6a5212371a647cac2b3c4f9d30bcd887/hotho}, keywords = {citation paper research sota dataset}, added-at = {2013-04-24T12:26:52.000+0200}, description = {}, interhash = {6a5212371a647cac2b3c4f9d30bcd887}, intrahash = {6a5212371a647cac2b3c4f9d30bcd887} } @electronic{socialcomputing.asu.edu, title = {Social Computing Data Repository at ASU}, url = {http://socialcomputing.asu.edu/}, biburl = {https://puma.uni-kassel.de/url/2fe9911693c4db7fc018f4995af70391/hotho}, keywords = {dataset friendster twitter}, added-at = {2013-04-20T20:32:39.000+0200}, description = {}, interhash = {2fe9911693c4db7fc018f4995af70391}, intrahash = {2fe9911693c4db7fc018f4995af70391} }