@proceedings{cellier2014proceedings, bibsource = {dblp computer science bibliography, http://dblp.org}, editor = {Cellier, Peggy and Charnois, Thierry and Hotho, Andreas and Matwin, Stan and Moens, Marie{-}Francine and Toussaint, Yannick}, interhash = {212d282598a034c37510c1c08c4f3a34}, intrahash = {cfb7265080d484cfda32e1fbdaff361f}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Proceedings of the 1st International Workshop on Interactions between Data Mining and Natural Language Processing co-located with The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, DMNLP@PKDD/ECML 2014, Nancy, France, September 15, 2014}, url = {http://ceur-ws.org/Vol-1202}, volume = 1202, year = 2014 } @article{atzmueller2014ubicon, abstract = {The combination of ubiquitous and social computing is an emerging research area which integrates different but complementary methods, techniques and tools. In this paper, we focus on the Ubicon platform, its applications, and a large spectrum of analysis results. Ubicon provides an extensible framework for building and hosting applications targeting both ubiquitous and social environments. We summarize the architecture and exemplify its implementation using four real-world applications built on top of Ubicon. In addition, we discuss several scientific experiments in the context of these applications in order to give a better picture of the potential of the framework, and discuss analysis results using several real-world data sets collected utilizing Ubicon.}, author = {Atzmueller, Martin and Becker, Martin and Kibanov, Mark and Scholz, Christoph and Doerfel, Stephan and Hotho, Andreas and Macek, Bjoern-Elmar and Mitzlaff, Folke and Mueller, Juergen and Stumme, Gerd}, doi = {10.1080/13614568.2013.873488}, interhash = {6364e034fa868644b30618dc887c0270}, intrahash = {176e4f2816af5fe1630ed65e062900ce}, journal = {New Review of Hypermedia and Multimedia}, number = 1, pages = {53--77}, title = {{Ubicon and its Applications for Ubiquitous Social Computing}}, url = {http://www.tandfonline.com/doi/abs/10.1080/13614568.2013.873488}, volume = 20, year = 2014 } @inproceedings{MASH:13b, address = {Bamberg, Germany}, author = {Mitzlaff, Folke and Atzmueller, Martin and Stumme, Gerd and Hotho, Andreas}, booktitle = {Proc. LWA 2013 (KDML Special Track)}, interhash = {73088600a500f7d06768615d6e1c2b3d}, intrahash = {820ffb2166b330bf60bb30b16e426553}, publisher = {University of Bamberg}, title = {{On the Semantics of User Interaction in Social Media (Extended Abstract, Resubmission)}}, year = 2011 } @article{hotho2010ubiquitous, author = {Hotho, Andreas and {Ulslev Pedersen}, Rasmus and Wurst, Michael}, interhash = {e779fb5dff41b65bce1aa38fdca4a376}, intrahash = {56f2940d5d0f2ce59c342d3b8ad42ca1}, issn = {0302-9743}, journal = {Lecture Notes in Computer Science}, number = 6202, pages = {61--74}, publisher = {Springer}, title = {Ubiquitous Data}, url = {http://rd.springer.com/content/pdf/10.1007%2F978-3-642-16392-0_4.pdf}, year = 2010 } @electronic{han2012mining, address = {Waltham, Mass.}, author = {Han, Jiawei and Kamber, Micheline and Pei, Jian}, interhash = {247a70f1f22ce1914e46d7ff6f43e378}, intrahash = {beb274b9aeaebb87f5423781b6839f54}, isbn = {0123814790}, publisher = {Morgan Kaufmann Publishers}, refid = {818321921}, title = {Data mining concepts and techniques, third edition}, url = {http://www.amazon.de/Data-Mining-Concepts-Techniques-Management/dp/0123814790/ref=tmm_hrd_title_0?ie=UTF8&qid=1366039033&sr=1-1}, year = 2012 } @book{han2011mining, address = {Amsterdam [u.a.]}, author = {Han, Jiawei and Kamber, Micheline}, interhash = {c94d7099d50ba439ee4579de99af285c}, intrahash = {1cf9e5362e9f34194abad46a4ff9c771}, isbn = {9780123814791 0123814790}, publisher = {Elsevier/Morgan Kaufmann}, refid = {734060711}, title = {Data mining : concepts and techniques}, url = {http://www.amazon.de/Data-Mining-Practical-Techniques-Management/dp/0123748569/ref=sr_1_2?ie=UTF8&qid=1366038862&sr=8-2&keywords=Data+mining}, year = 2011 } @book{north2012mining, author = {North, Matthew}, interhash = {c2a4d59bda60a400d2f1d45eefe68c93}, intrahash = {b382402685b65047b826d48260dca7d6}, isbn = {9780615684376 0615684378}, refid = {814299849}, title = {Data mining for the masses}, url = {http://www.amazon.de/Data-Mining-Masses-Matthew-North/dp/0615684378/ref=sr_1_1?s=books-intl-de&ie=UTF8&qid=1366038800&sr=1-1&keywords=rapidminer}, year = 2012 } @book{AH:12, address = {Bristol, UK}, editor = {Atzmueller, Martin and Hotho, Andreas}, interhash = {ad11fdb5a32814dc9c75b4483dccd6a7}, intrahash = {5304ffe0848eccd3938b50c811d2556d}, publisher = {Workshop Notes}, title = {{Proceedings of the Third International Workshop on Mining Ubiquitous and Social Environments (MUSE 2012)}}, url = {http://www.kde.cs.uni-kassel.de/ws/muse2012/proceedings.pdf}, year = 2012 } @book{ACHH:12, address = {Heidelberg, Germany}, editor = {Atzmueller, Martin and Chin, Alvin and Helic, Denis and Hotho, Andreas}, interhash = {ebf8e8b66c6c0723092e11e40998d61f}, intrahash = {a0e5d144b39199fa4acb6319f29e7a15}, publisher = {Springer Verlag}, series = {Lecture Notes in Computer Science}, title = {Modeling and Mining Ubiquitous Social Media}, url = {http://www.springer.com/computer/ai/book/978-3-642-33683-6}, volume = 7472, year = 2012 } @inproceedings{conf/birthday/BloehdornBCGHLMMSSV11, author = {Bloehdorn, Stephan and Blohm, Sebastian and Cimiano, Philipp and Giesbrecht, Eugenie and Hotho, Andreas and Lösch, Uta and Mädche, Alexander and Mönch, Eddie and Sorg, Philipp and Staab, Steffen and Völker, Johanna}, booktitle = {Foundations for the Web of Information and Services}, crossref = {conf/birthday/2011studer}, editor = {Fensel, Dieter}, ee = {http://dx.doi.org/10.1007/978-3-642-19797-0_7}, interhash = {db48314326a36fc4ac8770cba2c20e49}, intrahash = {21be5153a8f491c9f209d57ce7662387}, isbn = {978-3-642-19796-3}, pages = {115-142}, publisher = {Springer}, title = {Combining Data-Driven and Semantic Approaches for Text Mining.}, url = {http://dblp.uni-trier.de/db/conf/birthday/studer2011.html#BloehdornBCGHLMMSSV11}, year = 2011 } @inproceedings{conf/birthday/HothoS11, author = {Hotho, Andreas and Stumme, Gerd}, booktitle = {Foundations for the Web of Information and Services}, crossref = {conf/birthday/2011studer}, editor = {Fensel, Dieter}, ee = {http://dx.doi.org/10.1007/978-3-642-19797-0_8}, interhash = {502dc9bea95f0c581a37cd39cae2ff09}, intrahash = {845a2a6bf9a43be9e85741a6c7d2aa2d}, isbn = {978-3-642-19796-3}, pages = {143-153}, publisher = {Springer}, title = {From Semantic Web Mining to Social and Ubiquitous Mining - A Subjective View on Past, Current, and Future Research.}, url = {http://dblp.uni-trier.de/db/conf/birthday/studer2011.html#HothoS11}, year = 2011 } @book{AH:11, address = {Athens, Greece}, editor = {Atzmueller, Martin and Hotho, Andreas}, interhash = {8215abfd0550872bdd023c532f21e257}, intrahash = {87b0576f542aa6de352a2bff1428ce6b}, publisher = {ECML/PKDD 2011}, title = {{Proceedings of the 2011 International Workshop on Mining Ubiquitous and Social Environments (MUSE 2011)}}, year = 2011 } @inproceedings{mitzlaff2011community, author = {Mitzlaff, Folke and Atzmueller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {Analysis of Social Media and Ubiquitous Data}, interhash = {1ef065a81ed836dfd31fcc4cd4da133b}, intrahash = {0f45e870093c053e6f41f54c14bda46b}, series = {LNAI}, title = {{Community Assessment using Evidence Networks}}, volume = 6904, year = 2011 } @inproceedings{atzmueller2011towards, author = {Atzmueller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 4th international workshop on Social Data on the Web (SDoW2011)}, editor = {Passant, Alexandre and Fernández, Sergio and Breslin, John and Bojārs, Uldis}, interhash = {65222f0ccc23063a2a15c0a7fd5513a0}, intrahash = {a47a41658592202811f0139d4bb65871}, title = {Towards Mining Semantic Maturity in Social Bookmarking Systems}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/atzmueller2011towards.pdf}, year = 2011 } @inproceedings{conf/icdm/YassineH10, author = {Yassine, Mohamed and Hajj, Hazem}, booktitle = {ICDM Workshops}, crossref = {conf/icdm/2010w}, editor = {Fan, Wei and Hsu, Wynne and Webb, Geoffrey I. and Liu, Bing and Zhang, Chengqi and Gunopulos, Dimitrios and Wu, Xindong}, ee = {http://dx.doi.org/10.1109/ICDMW.2010.75}, interhash = {72ae8c258d6559e4a90370453ecc2acc}, intrahash = {8b0afeee143cec94f3058c214ae38c6f}, pages = {1136-1142}, publisher = {IEEE Computer Society}, title = {A Framework for Emotion Mining from Text in Online Social Networks.}, url = {http://dblp.uni-trier.de/db/conf/icdm/icdmw2010.html#YassineH10}, year = 2010 } @misc{Rubin2011, abstract = { Machine learning approaches to multi-label document classification have (to date) largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word tokens with different labels. We investigate the advantages of this approach relative to discriminative models, particularly with respect to classification problems involving large numbers of relatively rare labels. We compare the performance of generative and discriminative approaches on document labeling tasks ranging from datasets with several thousand labels to datasets with tens of labels. The experimental results indicate that generative models can achieve competitive multi-label classification performance compared to discriminative methods, and have advantages for datasets with many labels and skewed label frequencies. }, author = {Rubin, Timothy N. and Chambers, America and Smyth, Padhraic and Steyvers, Mark}, interhash = {e09d5d8587756d460a5d834025e75aac}, intrahash = {f8a5a3958ae264d19c7f5415eb7f0bce}, note = {cite arxiv:1107.2462}, title = {Statistical Topic Models for Multi-Label Document Classification}, url = {http://arxiv.org/abs/1107.2462}, year = 2011 } @book{srivastava2009mining, abstract = {Giving a broad perspective of the field from numerous vantage points, 'Text Mining' focuses on statistical methods for text mining and analysis. It examines methods to automatically cluster and classify text documents and applies these methods in a variety of areas.}, address = {Boca Raton, FL}, author = {Srivastava, Asho and Sahami, Mehran.}, interhash = {290eabe518274b6fbcc73a106a7d52a6}, intrahash = {45ab79501c114299142864becfa6c841}, isbn = {9781420059403 1420059408}, pages = {--}, publisher = {CRC Press}, refid = {144226505}, title = {Text mining : classification, clustering, and applications}, url = {http://www.worldcat.org/search?qt=worldcat_org_all&q=9781420059403}, year = 2009 } @article{march06crane, author = {Crane, Gregory}, doi = {10.1045/march2006-crane}, interhash = {36d4825e3189d89195693d1449e9aaea}, intrahash = {eea7ae2ac1480c84f87544f2942c28f2}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = {March }, number = 3, title = {What Do You Do with a Million Books?}, url = {http://www.dlib.org/dlib/march06/crane/03crane.html}, volume = 12, year = 2006 } @article{Berkhin05asurvey, abstract = {Abstract. This survey reviews the research related to PageRank computing. Components of a PageRank vector serve as authority weights for web pages independent of their textual content, solely based on the hyperlink structure of the web. PageRank is typically used as a web search ranking component. This defines the importance of the model and the data structures that underly PageRank processing. Computing even a single PageRank is a difficult computational task. Computing many PageRanks is a much more complex challenge. Recently, significant effort has been invested in building sets of personalized PageRank vectors. PageRank is also used in many diverse applications other than ranking. We are interested in the theoretical foundations of the PageRank formulation, in the acceleration of PageRank computing, in the effects of particular aspects of web graph structure on the optimal organization of computations, and in PageRank stability. We also review alternative models that lead to authority indices similar to PageRank and the role of such indices in applications other than web search. We also discuss linkbased search personalization and outline some aspects of PageRank infrastructure from associated measures of convergence to link preprocessing. 1.}, author = {Berkhin, Pavel}, interhash = {a0b85e8e85f88c262934f5fdd05525af}, intrahash = {50de350b2ae298909eef39a11d0f682c}, journal = {Internet Mathematics}, pages = {73--120}, title = {A survey on pagerank computing}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.2294}, volume = 2, year = 2005 } @incollection{Fayyad:1996:DMK:257938.257942, acmid = {257942}, address = {Menlo Park, CA, USA}, author = {Fayyad, Usama M. and Piatetsky-Shapiro, Gregory and Smyth, Padhraic}, chapter = {From data mining to knowledge discovery: an overview}, editor = {Fayyad, Usama M. and Piatetsky-Shapiro, Gregory and Smyth, Padhraic and Uthurusamy, Ramasamy}, interhash = {e62d85a492bbc917f43a5d9c8b775189}, intrahash = {d0b54b224b992e51d892d0f06d45cf6b}, isbn = {0-262-56097-6}, numpages = {34}, pages = {1--34}, publisher = {American Association for Artificial Intelligence}, title = {Advances in knowledge discovery and data mining}, url = {http://portal.acm.org/citation.cfm?id=257938.257942}, year = 1996 }