@article{1377474, title = {Tagging and searching: Search retrieval effectiveness of folksonomies on the World Wide Web}, address = {Tarrytown, NY, USA}, author = {P. Jason Morrison}, journal = {Inf. Process. Manage.}, number = 4, pages = {1562--1579}, publisher = {Pergamon Press, Inc.}, volume = 44, year = 2008, url = {http://portal.acm.org/citation.cfm?id=1377474}, issn = {0306-4573}, doi = {http://dx.doi.org/10.1016/j.ipm.2007.12.010}, description = {Tagging and searching}, abstract = {Many Web sites have begun allowing users to submit items to a collection and tag them with keywords. The folksonomies built from these tags are an interesting topic that has seen little empirical research. This study compared the search information retrieval (IR) performance of folksonomies from social bookmarking Web sites against search engines and subject directories. Thirty-four participants created 103 queries for various information needs. Results from each IR system were collected and participants judged relevance. Folksonomy search results overlapped with those from the other systems, and documents found by both search engines and folksonomies were significantly more likely to be judged relevant than those returned by any single IR system type. The search engines in the study had the highest precision and recall, but the folksonomies fared surprisingly well. Del.icio.us was statistically indistinguishable from the directories in many cases. Overall the directories were more precise than the folksonomies but they had similar recall scores. Better query handling may enhance folksonomy IR performance further. The folksonomies studied were promising, and may be able to improve Web search performance.}, biburl = {http://www.bibsonomy.org/bibtex/27e1dc3f52085093cc33d8fe931253b34/hotho}, keywords = {ir retrieval toread performance engine folksonomy comparision search} } @misc{white-2005, title = {A generative model for feedback networks}, author = {Douglas R. White and Natasa Kejzar and Constantino Tsallis and Doyne Farmer and Scott White}, year = 2005, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cond-mat/0508028}, description = {[cond-mat/0508028] A generative model for feedback networks}, abstract = { We investigate a simple generative model for network formation. The model is designed to describe the growth of networks of kinship, trading, corporate alliances, or autocatalytic chemical reactions, where feedback is an essential element of network growth. The underlying graphs in these situations grow via a competition between cycle formation and node addition. After choosing a given node, a search is made for another node at a suitable distance. If such a node is found, a link is added connecting this to the original node, and increasing the number of cycles in the graph; if such a node cannot be found, a new node is added, which is linked to the original node. We simulate this algorithm and find that we cannot reject the hypothesis that the empirical degree distribution is a q-exponential function, which has been used to model long-range processes in nonequilibrium statistical mechanics.}, biburl = {http://www.bibsonomy.org/bibtex/2dd7cd33e8a95a0128fe05adc46483ac7/hotho}, keywords = {network model toread} } @inproceedings{1379123, title = {Logsonomy - social information retrieval with logdata}, address = {New York, NY, USA}, author = {Beate Krause and Robert Jäschke and Andreas Hotho and Gerd Stumme}, booktitle = {HT '08: Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, pages = {157--166}, publisher = {ACM}, year = 2008, url = {http://portal.acm.org/citation.cfm?id=1379092.1379123&coll=ACM&dl=ACM&type=series&idx=SERIES399&part=series&WantType=Proceedings&title=HT&CFID=825963&CFTOKEN=78379687}, location = {Pittsburgh, PA, USA}, isbn = {978-1-59593-985-2}, doi = {http://doi.acm.org/10.1145/1379092.1379123}, description = {HT: HT '08, Logsonomy - social information ...}, abstract = {Social bookmarking systems constitute an established part of the Web 2.0. In such systems users describe bookmarks by keywords called tags. The structure behind these social systems, called folksonomies, can be viewed as a tripartite hypergraph of user, tag and resource nodes. This underlying network shows specific structural properties that explain its growth and the possibility of serendipitous exploration. Today's search engines represent the gateway to retrieve information from the World Wide Web. Short queries typically consisting of two to three words describe a user's information need. In response to the displayed results of the search engine, users click on the links of the result page as they expect the answer to be of relevance. This clickdata can be represented as a folksonomy in which queries are descriptions of clicked URLs. The resulting network structure, which we will term logsonomy is very similar to the one of folksonomies. In order to find out about its properties, we analyze the topological characteristics of the tripartite hypergraph of queries, users and bookmarks on a large snapshot of del.icio.us and on query logs of two large search engines. All of the three datasets show small world properties. The tagging behavior of users, which is explained by preferential attachment of the tags in social bookmark systems, is reflected in the distribution of single query words in search engines. We can conclude that the clicking behaviour of search engine users based on the displayed search results and the tagging behaviour of social bookmarking users is driven by similar dynamics.}, biburl = {http://www.bibsonomy.org/bibtex/2c7f43f2f922de1e7febedd10347e80cb/hotho}, keywords = {2.0 2008 myown logsonomy folksonomy web} } @inproceedings{anti2008krause, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, author = {Beate Krause and Christoph Schmitz and Andreas Hotho and Gerd Stumme}, booktitle = {Proc. of the Fourth International Workshop on Adversarial Information Retrieval on the Web}, year = 2008, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, biburl = {http://www.bibsonomy.org/bibtex/26357f535000a383f228f1e8e56ca86ca/hotho}, keywords = {2008 spam ml bookmarking social myown classification dm folksonomy mining} } @inproceedings{PuWang:2007, title = {Improving Text Classification by Using Encyclopedia Knowledge}, author = {Pu Wang and Jian Hu and Hua-Jun Zeng and Lijun Chen and Zheng Chen}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, pages = {332-341}, year = 2007, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, issn = {1550-4786}, isbn = {978-0-7695-3018-5}, doi = {10.1109/ICDM.2007.77}, description = {Welcome to IEEE Xplore 2.0: Improving Text Classification by Using Encyclopedia Knowledge}, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.}, biburl = {http://www.bibsonomy.org/bibtex/266058efbca5abd1222f72c32365d23fa/steff83}, keywords = {text learning ontology master_thesis classification wikipedia} } @inproceedings{PuWang:2007, title = {Improving Text Classification by Using Encyclopedia Knowledge}, author = {Pu Wang and Jian Hu and Hua-Jun Zeng and Lijun Chen and Zheng Chen}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, pages = {332-341}, year = 2007, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, issn = {1550-4786}, isbn = {978-0-7695-3018-5}, doi = {10.1109/ICDM.2007.77}, description = {Welcome to IEEE Xplore 2.0: Improving Text Classification by Using Encyclopedia Knowledge}, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.}, biburl = {http://www.bibsonomy.org/bibtex/266058efbca5abd1222f72c32365d23fa/hotho}, keywords = {toread text classification ontology learning wikipedia} } @proceedings{Zhu1583, title = {Dynamic Hierarchical Markov Random Fields for Integrated Web Data Extraction }, author = {Jun Zhu and Zaiqing Nie and Bo Zhang and Ji-Rong Wen}, volume = {v9}, year = 1583, url = {http://www.jmlr.org/papers/volume9/zhu08a/zhu08a.pdf}, page = {1583--1614}, biburl = {http://www.bibsonomy.org/bibtex/2534bb3931ebf4a537d7d4e3c85788632/hotho}, keywords = {toread} } @techreport{fawcett04roc, title = {ROC Graphs: Notes and Practical Considerations for Researchers}, author = {T. Fawcett}, howpublished = {Tech Report HPL-2003-4}, institution = {HP Laboratories}, year = 2004, url = {http://www.hpl.hp.com/techreports/2003/HPL-2003-4.pdf}, description = {ROC Graphs: Notes and Practical Considerations for Researchers}, biburl = {http://www.bibsonomy.org/bibtex/2c580a50d58db5cd78d7dc5ab3cbd2a29/hotho}, keywords = {auc tutorial roc evaluation} } @article{Pang2008, title = {Opinion mining and sentiment analysis}, author = {Bo Pang and Lillian Lee}, journal = {Foundations and Trends® in Information Retrieval}, number = {1-2}, pages = {1-135}, volume = 2, year = 2008, url = {http://www.cs.cornell.edu/home/llee/omsa/omsa-published.pdf}, isbn = {978-1-60198-150-9}, date = {July 2008}, tech = {Now publishers}, description = {Lillian Lee's Home Page}, biburl = {http://www.bibsonomy.org/bibtex/2236d4f703fda3dd9457863f28eda56cb/hotho}, keywords = {mining analysis toread opinion sentiment} } @misc{ailon-2007, title = {An efficient reduction of ranking to classification}, author = {Nir Ailon and Mehryar Mohri}, year = 2007, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0710.2889}, description = {[0710.2889] An efficient reduction of ranking to classification}, abstract = { This paper describes an efficient reduction of the learning problem of ranking to binary classification. The reduction guarantees an average pairwise misranking regret of at most that of the binary classifier regret, improving a recent result of Balcan et al which only guarantees a factor of 2. Moreover, our reduction applies to a broader class of ranking loss functions, admits a simpler proof, and the expected running time complexity of our algorithm in terms of number of calls to a classifier or preference function is improved from $\Omega(n^2)$ to $O(n \log n)$. In addition, when the top $k$ ranked elements only are required ($k \ll n$), as in many applications in information extraction or search engines, the time complexity of our algorithm can be further reduced to $O(k \log k + n)$. Our reduction and algorithm are thus practical for realistic applications where the number of points to rank exceeds several thousands. Much of our results also extend beyond the bipartite case previously studied.}, biburl = {http://www.bibsonomy.org/bibtex/2d8bd1b99e3c245d17b577514727ebff2/hotho}, keywords = {ranking learning toread} } @inproceedings{Detecting_Commmunities_via_Simultaneous_Clustering_of_Graphs_and_Folksonomies, title = {{Detecting Commmunities via Simultaneous Clustering of Graphs and Folksonomies}}, author = {Akshay Java and Anupam Joshi and Tim Finin}, booktitle = {WebKDD 2008 Workshop on Web Mining and Web Usage Analysis}, month = {August}, note = {To Appear}, year = 2008, biburl = {http://www.bibsonomy.org/bibtex/2645abd6b3191a2a6e844d7542651ed1c/hotho}, keywords = {toread community clusterig folksonomy detection} } @inproceedings{cimiano2003automatic, title = {Automatic Acquisition of Taxonomies from Text: FCA meets NLP}, address = {Cavtat-Dubrovnik, Croatia}, author = {Philipp Cimiano and Steffen Staab and Julien Tane}, booktitle = {Proceedings of the ECML / PKDD Workshop on Adaptive Text Extraction and Mining}, pages = {10--17}, year = 2003, url = {http://www.dcs.shef.ac.uk/~fabio/ATEM03/cimiano-ecml03-atem.pdf}, biburl = {http://www.bibsonomy.org/bibtex/2573ac0e71d6b1c369cf881ddda8c7841/steff83}, keywords = {evaluation taxonomic_overlap ontology_learning master_thesis} } @inproceedings{AlKhalifa:2007, title = {CoolRank: A Social Solution for Ranking Bookmarked Web Resources}, author = {H.S. Al-Khalifa}, booktitle = {Innovations in Information Technology, 2007. Innovations '07. 4th International Conference on}, pages = {208-212}, year = 2007, url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4430482}, isbn = {978-1-4244-1841-1}, doi = {10.1109/IIT.2007.4430482}, description = {Welcome to IEEE Xplore 2.0: CoolRank: A Social Solution for Ranking Bookmarked Web Resources}, abstract = {Users tag resources for a variety of reasons and using a variety of conventions. The tags that they provide are stored in social bookmarking services, so these services can provide a rich gateway to a wide and interesting quantity of web resources. The cognitive effort that has gone into making these tags has presumably added value to the description of the resource. In this work we utilize the quantitative value of these tags for ranking bookmarked web resources in social bookmarking services. Our proposed solution is called CoolRank, a simple and intuitive model to rank bookmarked web resources in a social bookmarking service, such as del.icio.us. CoolRank makes use of both quantitative information, based on the number of people who have bookmarked a web resource, and subjective information, based on the words people have used in their tags.}, biburl = {http://www.bibsonomy.org/bibtex/24671fb1c606e3d7f559bb25d9b20e47d/hotho}, keywords = {toread * web ranking folksonomy 2.0 folkrank} } @inproceedings{IfrimTW-ICML2005, title = {Learning Word-to-Concept Mappings for Automatic Text Classification}, address = {Bonn, Germany}, author = {Georgiana Ifrim and Martin Theobald and Gerhard Weikum}, booktitle = {Proceedings of the 22nd International Conference on Machine Learning - Learning in Web Search (LWS 2005)}, editor = {Luc De Raedt and Stefan Wrobel}, pages = {18--26}, year = 2005, url = {http://www.mpi-inf.mpg.de/~ifrim/publications/icml-lws05.pdf}, isbn = {1-59593-180-5}, description = {D5 MPI-INF Publications: Proceedings Article: Learning Word-to-Concept Mappings for Automatic Text Classification}, biburl = {http://www.bibsonomy.org/bibtex/257f8241941ed979455c3dbb90893020f/hotho}, keywords = {classification tc text topic model wordnet concept} } @inbook{hotho2008bookmarking, title = {Social Bookmarking}, address = {München}, author = {Andreas Hotho}, booktitle = {Web 2.0 in der Unternehmenspraxis: Grundlagen, Fallstudien und Trends zum Einsatz von Social Software}, editor = {Andrea Back and Norbert Gronau and Klaus Tochtermann}, pages = {26-38}, publisher = {Oldenbourg Verlag}, year = 2008, url = {http://www.amazon.de/gp/redirect.html%3FASIN=3486585797%26tag=ws%26lcode=xm2%26cID=2025%26ccmID=165953%26location=/Web-2-0-Unternehmenspraxis-Grundlagen-Fallstudien/dp/3486585797%253FSubscriptionId=13CT5CVB80YFWJEPWS02}, ean = {9783486585797}, asin = {3486585797}, isbn = {9783486585797}, biburl = {http://www.bibsonomy.org/bibtex/2b54f6557893e3ab9d1eb83b0baeb136e/hotho}, keywords = {folksonomy 2008 bookmarking social myown} } @inproceedings{hotho2006emergent, title = {Emergent Semantics in BibSonomy}, address = {Bonn}, author = {Andreas Hotho and Robert Jäschke and Christoph Schmitz and Gerd Stumme}, booktitle = {Informatik 2006 - Informatik für Menschen. Band 2}, editor = {Christian Hochberger and Rüdiger Liskowsky}, month = {oct}, note = {Proc. Workshop on Applications of Semantic Technologies, Informatik 2006}, publisher = {Gesellschaft für Informatik}, series = {Lecture Notes in Informatics}, volume = {P-94}, year = 2006, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006emergent.pdf}, abstract = {Social bookmark tools are rapidly emerging on the Web. In suchsystems users are setting up lightweight conceptual structurescalled folksonomies. The reason for their immediate success is thefact that no specific skills are needed for participating. In thispaper we specify a formal model for folksonomies, briefly describeour own system BibSonomy, which allows for sharing both bookmarks andpublication references, and discuss first steps towards emergent semantics.}, biburl = {http://www.bibsonomy.org/bibtex/205043cc20f1e0f5a612135c970e4f1ac/steff83}, keywords = {semantics master_thesis emergent folksonomy} } @inproceedings{jaeschke2006wege, title = {Wege zur Entdeckung von Communities in Folksonomies}, address = {Halle-Wittenberg}, author = {Robert Jäschke and Andreas Hotho and Christoph Schmitz and Gerd Stumme}, booktitle = {Proc. 18. Workshop Grundlagen von Datenbanken}, editor = {Stefan Braß and Alexander Hinneburg}, month = {June}, pages = {80-84}, publisher = {Martin-Luther-Universität }, year = 2006, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/jaeschke2006wege.pdf}, abstract = {Ein wichtiger Baustein des neu entdeckten World Wide Web -- des "`Web 2.0"' -- stellenFolksonomies dar. In diesen Systemen können Benutzer gemeinsam Ressourcen verwalten undmit Schlagwörtern versehen. Die dadurch entstehenden begrifflichen Strukturen stellenein interessantes Forschungsfeld dar. Dieser Artikel untersucht Ansätze und Wege zur Entdeckung und Strukturierung von Nutzergruppen ("Communities") in Folksonomies.}, biburl = {http://www.bibsonomy.org/bibtex/22b6be3bd5daee7119973fcf69909956f/steff83}, keywords = {master_thesis communities folksonomy} } @article{jaeschke2008discovering, title = {Discovering Shared Conceptualizations in Folksonomies}, author = {Robert Jäschke and Andreas Hotho and Christoph Schmitz and Bernhard Ganter and Gerd Stumme}, booktitle = {Semantic Web and Web 2.0}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, month = {feb}, note = { }, number = 1, pages = {38--53}, volume = 6, year = 2008, url = {http://www.sciencedirect.com/science/article/B758F-4R53WD4-1/2/ae56bd6e7132074272ca2035be13781b}, description = {ScienceDirect - Web Semantics: Science, Services and Agents on the World Wide Web : Discovering shared conceptualizations in folksonomies}, abstract = {Social bookmarking tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. Unlike ontologies, shared conceptualizations are not formalized, but rather implicit. We present a new data mining task, the mining of all frequent tri-concepts, together with an efficient algorithm, for discovering these implicit shared conceptualizations. Our approach extends the data mining task of discovering all closed itemsets to three-dimensional data structures to allow for mining folksonomies. We provide a formal definition of the problem, and present an efficient algorithm for its solution. Finally, we show the applicability of our approach on three large real-world examples.}, biburl = {http://www.bibsonomy.org/bibtex/263901930c137df0c2dad84075c564b14/hotho}, keywords = {2008 tagging fca folksonomy myown discovering analysis concept formal bibsonomy} } @article{voelker2008aeon, title = {AEON - An Approach to the Automatic Evaluation of Ontologies}, author = {Johanna Völker and Denny Vrandecic and York Sure and Andreas Hotho}, journal = {Journal of Applied Ontology}, note = {to appear}, year = 2008, url = {http://ontoware.org/projects/aeon/}, description = {Institut AIFB - Publikation: AEON - An Approach to the Automatic Evaluation of Ontologies}, biburl = {http://www.bibsonomy.org/bibtex/2ea55fe7088ef25cdf060d30d94a09e26/hotho}, keywords = {sw ontology 2008 evaluation myown ml automatic} } @proceedings{semweb2007esoe, title = {Proceedings of the First International Workshop on Emergent Semantics and Ontology Evolution, ESOE 2007, co-located with ISWC 2007 + ASWC 2007, Busan, Korea, November 12th, 2007}, booktitle = {ESOE}, editor = {Liming Chen and Philippe Cudré-Mauroux and Peter Haase and Andreas Hotho and Ernie Ong}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, volume = 292, year = 2007, url = {http://dblp.uni-trier.de/db/conf/semweb/esoe2007.html}, date = {2008-06-02}, description = {dblp}, biburl = {http://www.bibsonomy.org/bibtex/26a076256fc0fbf774cd5e67addc13641/hotho}, keywords = {2007 workshop semantics ontology myown} }