For each of the contexts we use the same probabilistic model and Borda Count based aggregation approach to generate recommendations from different contexts into a unified ranking of recommended tags. We evaluate our system using a large set of real-world data from Flickr. We show that by using personalised contexts we can significantly improve tag recommendation compared to using collective knowledge alone. We also analyse our experimental results to explore the capabilities of our system with respect to a user's social behaviour.}, address = {Paris, France}, author = {Rae, Adam and Sigurbjörnsson, Börkur and van Zwol, Roelof}, booktitle = {Adaptivity, Personalization and Fusion of Heterogeneous Information}, interhash = {2595ff47e852a64c7f1c88b915c7e9ad}, intrahash = {98034c615577fd3558fd326fbe03f894}, location = {Paris, France}, pages = {92--99}, publisher = {Le Centre De Hautes Etudes Internationales d'Informatique Documentaire}, series = {RIAO '10}, title = {Improving tag recommendation using social networks}, url = {http://portal.acm.org/citation.cfm?id=1937055.1937077}, year = 2010 } @inproceedings{conf/sigir/GuanBMCW09, author = {Guan, Ziyu and Bu, Jiajun and Mei, Qiaozhu and Chen, Chun and Wang, Can}, booktitle = {SIGIR}, crossref = {conf/sigir/2009}, editor = {Allan, James and Aslam, Javed A. and Sanderson, Mark and Zhai, ChengXiang and Zobel, Justin}, ee = {http://doi.acm.org/10.1145/1571941.1572034}, interhash = {53d2e8bc966048bc01efcc57b2fc8250}, intrahash = {ac9427acf51cbf7cb5a35f66a16a32c0}, isbn = {978-1-60558-483-6}, pages = {540-547}, publisher = {ACM}, title = {Personalized tag recommendation using graph-based ranking on multi-type interrelated objects.}, url = {http://www-personal.umich.edu/~qmei/pub/sigir09-tag.pdf}, year = 2009 } @inproceedings{krestel2008art, abstract = {
Collaborative tagging, supported by many social networking websites, is currently enjoying an increasing popularity. The usefulness of this largely available tag data has been explored in many applications including web resources categorization,deriving emergent semantics, web search etc. However, since tags are supplied by users <em>freely</em> , not all of them are useful and reliable, especially when they are generated by spammers with malicious intent. Therefore, identifying tags of high quality is crucial in improving the performance of applications based on tags. In this paper, we propose TRP-Rank (Tag-Resource Pair Rank), an algorithm to measure the quality of tags by manually assessing a seed set and <em>propagating the quality</em> through a graph. The three dimensional relationship among users, tags and web resources is firstly represented by a graph structure. A set of seed nodes, where each node represents a tag annotating a resource, is then selected and their quality is assessed. The quality of the remaining nodes is calculated by propagating the known quality of the seeds through the graph structure. We evaluate our approach on a public data set where tags generated by suspicious spammers were manually labelled. The experimental results demonstrate the effectiveness of this approach in measuring the quality of tags.
}, acmid = {1484165}, address = {Berlin, Heidelberg}, author = {Krestel, Ralf and Chen, Ling}, booktitle = {Proceedings of the 3rd Asian Semantic Web Conference on The Semantic Web}, doi = {10.1007/978-3-540-89704-0_18}, interhash = {44401088956f59c92c11f6a910ed4df4}, intrahash = {dc00da9179d556ce047c1b41eb815e21}, isbn = {978-3-540-89703-3}, location = {Bangkok, Thailand}, numpages = {15}, pages = {257--271}, publisher = {Springer-Verlag}, series = {ASWC '08}, title = {The Art of Tagging: Measuring the Quality of Tags}, url = {http://dx.doi.org/10.1007/978-3-540-89704-0_18}, year = 2008 } @inproceedings{cattuto2008semantic, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks like synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Eventhough most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptionson the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity interms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures oftag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding isprovided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measuresof semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of theinvestigated similarity measures and indicates which ones are better suited in the context of a given semantic application.}, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {The Semantic Web - ISWC 2008}, doi = {10.1007/978-3-540-88564-1_39}, interhash = {b44538648cfd476d6c94e30bc6626c86}, intrahash = {4752f261d03cead0c52565148a0ba1c9}, isbn = {978-3-540-88563-4}, pages = {615--631}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf}, volume = 5318, year = 2008 } @inproceedings{illigtoappearcomparison, author = {Illig, Jens and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {Postproceedings of the International Conference on Knowledge Processing in Practice (KPP2007)}, file = {:illig2009comparison.pdf:PDF}, interhash = {849cc8141815da667268acd7389d610a}, intrahash = {65f66d8e45722648f0471a193dd8ead6}, publisher = {Springer}, title = {A Comparison of content-based Tag Recommendations in Folksonomy Systems}, year = {to appear} } @inproceedings{cattuto2008semantica, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For taskslike synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Eventhough most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptionson the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity interms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures oftag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding isprovided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measuresof semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of theinvestigated similarity measures and indicates which ones are better suited in the context of a given semantic application.}, address = {Heidelberg}, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008}, doi = {http://dx.doi.org/10.1007/978-3-540-88564-1_39}, editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad}, file = {cattuto2008semantica.pdf:cattuto2008semantica.pdf:PDF}, groups = {public}, interhash = {b44538648cfd476d6c94e30bc6626c86}, intrahash = {27198c985b3bdb6daab0f7e961b370a9}, pages = {615--631}, publisher = {Springer}, series = {LNAI}, timestamp = {2009-09-14 19:12:46}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2008semantica.pdf}, username = {dbenz}, volume = 5318, year = 2008 } @book{jaeschke2011formal, abstract = {One of the most noticeable innovation that emerged with the advent of the Web 2.0 and the focal point of this thesis are collaborative tagging systems. They allow users to annotate arbitrary resources with freely chosen keywords, so called tags. The tags are used for navigation, finding resources, and serendipitous browsing and thus provide an immediate benefit for the user. By now, several systems for tagging photos, web links, publication references, videos, etc. have attracted millions of users which in turn annotated countless resources. Tagging gained so much popularity that it spread into other applications like web browsers, software packet managers, and even file systems. Therefore, the relevance of the methods presented in this thesis goes beyond the Web 2.0. The conceptual structure underlying collaborative tagging systems is called folksonomy. It can be represented as a tripartite hypergraph with user, tag, and resource nodes. Each edge of the graph expresses the fact that a user annotated a resource with a tag. This social network constitutes a lightweight conceptual structure that is not formalized, but rather implicit and thus needs to be extracted with knowledge discovery methods. In this thesis a new data mining task – the mining of all frequent tri-concepts – is presented, together with an efficient algorithm for discovering such 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. Extending the theory of triadic Formal Concept Analysis, we provide a formal definition of the problem, and present an efficient algorithm for its solution. We show the applicability of our approach on three large real-world examples and thereby perform a conceptual clustering of two collaborative tagging systems. Finally, we introduce neighborhoods of triadic concepts as basis for a lightweight visualization of tri-lattices. The social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind, has been developed by our research group. Besides being a useful tool for many scientists, it provides interested researchers a basis for the evaluation and integration of their knowledge discovery methods. This thesis introduces BibSonomy as an exemplary collaborative tagging system and gives an overview of its architecture and some of its features. Furthermore, BibSonomy is used as foundation for evaluating and integrating some of the discussed approaches. Collaborative tagging systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In this thesis we evaluate and compare several recommendation algorithms on large-scale real-world datasets: an adaptation of user-based Collaborative Filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag co-occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag co-occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We demonstrate how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender. Furthermore, we show how to integrate recommendation methods into a real tagging system, record and evaluate their performance by describing the tag recommendation framework we developed for BibSonomy. With the intention to develop, test, and evaluate recommendation algorithms and supporting cooperation with researchers, we designed the framework to be easily extensible, open for a variety of methods, and usable independent from BibSonomy. We also present an evaluation of the framework which demonstrates its power. The folksonomy graph shows specific structural properties that explain its growth and the possibility of serendipitous exploration. Clicklogs of web search engines 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 folksonomy snapshot and on query logs of two large search engines. We find that all of the three datasets exhibit similar structural properties and thus conclude that the clicking behaviour of search engine users based on the displayed search results and the tagging behaviour of collaborative tagging users is driven by similar dynamics. In this thesis we further transfer the folksonomy paradigm to the Social Semantic Desktop – a new model of computer desktop that uses Semantic Web technologies to better link information items. There we apply community support methods to the folksonomy found in the network of social semantic desktops. Thus, we connect knowledge discovery for folksonomies with semantic technologies. Alltogether, the research in this thesis is centered around collaborative tagging systems and their underlying datastructure – folksonomies – and thereby paves the way for the further dissemination of this successful knowledge management paradigm. }, address = {Heidelberg, Germany}, author = {Jäschke, Robert}, interhash = {dcb2cd1cd72ae45d77c4d8755d199405}, intrahash = {9db90c2ff04f514ada9f6b50fde46065}, isbn = {978-3-89838-332-5}, month = jan, publisher = {Akademische Verlagsgesellschaft AKA}, series = {Dissertationen zur Künstlichen Intelligenz}, title = {Formal Concept Analysis and Tag Recommendations in Collaborative Tagging Systems}, url = {http://www.aka-verlag.com/de/detail?ean=978-3-89838-332-5}, vgwort = {413}, volume = 332, year = 2011 } @article{jaeschke2008tag, abstract = {Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender. }, address = {Amsterdam}, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, doi = {10.3233/AIC-2008-0438}, editor = {Giunchiglia, Enrico}, interhash = {b2f1aba6829affc85d852ea93a8e39f7}, intrahash = {955bcf14f3272ba6eaf3dadbef6c0b10}, issn = {0921-7126}, journal = {AI Communications}, month = dec, number = 4, pages = {231--247}, publisher = {IOS Press}, title = {Tag Recommendations in Social Bookmarking Systems}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/jaeschke2008tag.pdf}, vgwort = {63}, volume = 21, year = 2008 } @article{jaeschke2008tag, abstract = {Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender. }, address = {Amsterdam}, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, doi = {10.3233/AIC-2008-0438}, editor = {Giunchiglia, Enrico}, interhash = {b2f1aba6829affc85d852ea93a8e39f7}, intrahash = {955bcf14f3272ba6eaf3dadbef6c0b10}, issn = {0921-7126}, journal = {AI Communications}, number = 4, pages = {231-247}, publisher = {IOS Press}, title = {Tag Recommendations in Social Bookmarking Systems}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, vgwort = {63}, volume = 21, year = 2008 } @article{jaeschke2008tag, abstract = {Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender. }, address = {Amsterdam}, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, doi = {10.3233/AIC-2008-0438}, editor = {Giunchiglia, Enrico}, interhash = {b2f1aba6829affc85d852ea93a8e39f7}, intrahash = {955bcf14f3272ba6eaf3dadbef6c0b10}, issn = {0921-7126}, journal = {AI Communications}, number = 4, pages = {231-247}, publisher = {IOS Press}, title = {Tag Recommendations in Social Bookmarking Systems}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, vgwort = {63}, volume = 21, year = 2008 } @inproceedings{rendle2009learning, abstract = {Tag recommendation is the task of predicting a personalized list of tags for a user given an item. This is important for many websites with tagging capabilities like last.fm or delicious. In this paper, we propose a method for tag recommendation based on tensor factorization (TF). In contrast to other TF methods like higher order singular value decomposition (HOSVD), our method RTF ('ranking with tensor factorization') directly optimizes the factorization model for the best personalized ranking. RTF handles missing values and learns from pairwise ranking constraints. Our optimization criterion for TF is motivated by a detailed analysis of the problem and of interpretation schemes for the observed data in tagging systems. In all, RTF directly optimizes for the actual problem using a correct interpretation of the data. We provide a gradient descent algorithm to solve our optimization problem. We also provide an improved learning and prediction method with runtime complexity analysis for RTF. The prediction runtime of RTF is independent of the number of observations and only depends on the factorization dimensions. Besides the theoretical analysis, we empirically show that our method outperforms other state-of-the-art tag recommendation methods like FolkRank, PageRank and HOSVD both in quality and prediction runtime.}, address = {New York, NY, USA}, author = {Rendle, Steffen and Balby Marinho, Leandro and Nanopoulos, Alexandros and Schmidt-Thieme, Lars}, booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {10.1145/1557019.1557100}, interhash = {1cc85ca2ec82db2a3caf40fd1795a58a}, intrahash = {1bd672ffb8d6ba5589bb0c7deca09412}, isbn = {978-1-60558-495-9}, location = {Paris, France}, pages = {727--736}, publisher = {ACM}, title = {Learning optimal ranking with tensor factorization for tag recommendation}, url = {http://portal.acm.org/citation.cfm?doid=1557019.1557100}, year = 2009 } @inproceedings{1454017, address = {New York, NY, USA}, author = {Symeonidis, Panagiotis and Nanopoulos, Alexandros and Manolopoulos, Yannis}, booktitle = {RecSys '08: Proceedings of the 2008 ACM conference on Recommender systems}, doi = {http://doi.acm.org/10.1145/1454008.1454017}, interhash = {8ee38f4ffc05845fcb98f121fb265d48}, intrahash = {e93afe409833a632af02290bbe134cba}, isbn = {978-1-60558-093-7}, location = {Lausanne, Switzerland}, pages = {43--50}, publisher = {ACM}, title = {Tag recommendations based on tensor dimensionality reduction}, url = {http://portal.acm.org/citation.cfm?id=1454017}, year = 2008 } @inproceedings{cattuto2008semantic, abstract = {Collaborative tagging systems have nowadays become important data sources for populating semantic web applications. For tasks like synonym detection and discovery of concept hierarchies, many researchers introduced measures of tag similarity. Eventhough most of these measures appear very natural, their design often seems to be rather ad hoc, and the underlying assumptionson the notion of similarity are not made explicit. A more systematic characterization and validation of tag similarity interms of formal representations of knowledge is still lacking. Here we address this issue and analyze several measures oftag similarity: Each measure is computed on data from the social bookmarking system del.icio.us and a semantic grounding isprovided by mapping pairs of similar tags in the folksonomy to pairs of synsets in Wordnet, where we use validated measuresof semantic distance to characterize the semantic relation between the mapped tags. This exposes important features of theinvestigated similarity measures and indicates which ones are better suited in the context of a given semantic application.}, address = {Heidelberg}, author = {Cattuto, Ciro and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {The Semantic Web -- ISWC 2008, Proc.Intl. Semantic Web Conference 2008}, editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad}, interhash = {b44538648cfd476d6c94e30bc6626c86}, intrahash = {27198c985b3bdb6daab0f7e961b370a9}, pages = {615--631}, publisher = {Springer}, series = {LNAI}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, url = {http://dx.doi.org/10.1007/978-3-540-88564-1_39}, volume = 5318, year = 2008 } @inproceedings{markines2009evaluating, abstract = {Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We ?nd that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity.}, author = {Markines, Benjamin and Cattuto, Ciro and Menczer, Filippo and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {18th International World Wide Web Conference}, interhash = {a266558ad4d83d536a0be2ac94b6b7df}, intrahash = {d16e752a8295d5dad7e26b199d9f614f}, month = {April}, pages = {641--650}, title = {Evaluating Similarity Measures for Emergent Semantics of Social Tagging}, url = {http://www2009.eprints.org/65/}, year = 2009 } @incollection{m2009nliches, author = {Dittmann, C. and Dittmann, M. and Peters, I. and Weller, K.}, booktitle = {Generation international - die Zukunft von Information, Wissenschaft und Profession. Proceedings der 31. Online-Tagung der Germany.}, date = {(2009)}, editor = {Ockenfeld, M.}, interhash = {8b30444eb1620594515e720f6ea04def}, intrahash = {32b5372ad9fb2c2932224454cd869afa}, note = {Frankfurt am Main: DGI}, pages = {117-128}, publisher = {DGI Frankfurt a. M.}, title = {Persönliches Tag Gardening mit tagCare.}, url = {http://wwwalt.phil-fak.uni-duesseldorf.de/infowiss/content/mitarbeiter/peters.php}, year = 2009 }