@incollection{LA:12, author = {Lemmerich, Florian and Atzmueller, Martin}, title = {Describing Locations using Tags and Images: Explorative Pattern Mining in Social Media}, booktitle = {Modeling and Mining Ubiquitous Social Media}, series = {LNAI}, publisher = {Springer Verlag}, address = {Heidelberg, Germany}, year = {2012}, volume = {7472}, url = {http://www.kde.cs.uni-kassel.de/atzmueller/paper/lemmerich-explorative-pattern-mining-socia-media-lnai-2012.pdf}, keywords = {2012, collective, data, describing, explorative, images, intelligence, itegpub, locations, media, mining, social, tags, ubiquitous, venus} }

%0 = incollection %A = Lemmerich, Florian and Atzmueller, Martin %B = Modeling and Mining Ubiquitous Social Media %C = Heidelberg, Germany %D = 2012 %I = Springer Verlag %T = Describing Locations using Tags and Images: Explorative Pattern Mining in Social Media %U = http://www.kde.cs.uni-kassel.de/atzmueller/paper/lemmerich-explorative-pattern-mining-socia-media-lnai-2012.pdf

We propose to integrate various pieces of information about a web page (search queries, social annotations, terms extracted from the pagetext) into a navigational menu. This menu displays an auxiliary set of tags (navigational tags) selected with the goal of helping user navigation. We propose a novel framework (navigational utility) for comparing different tag selection methods. We also investigate which source of tags is more suitable for our scenario and we conclude that tags extracted from search queries (query tags) are more appropriate.

@techreport{antonellis2011navigating, author = {Antonellis, Ioannis and Karim, Jawed and Garcia-Molina, Hector}, title = {Navigating the Web with Query Tags}, publisher = {Stanford InfoLab}, type = {Technical Report}, year = {2011}, url = {http://ilpubs.stanford.edu:8090/943/}, keywords = {folksonomies, navigation, query_tags, tags}, abstract = {We propose to integrate various pieces of information about a web page (search queries, social annotations, terms extracted from the pagetext) into a navigational menu. This menu displays an auxiliary set of tags (navigational tags) selected with the goal of helping user navigation. We propose a novel framework (navigational utility) for comparing different tag selection methods. We also investigate which source of tags is more suitable for our scenario and we conclude that tags extracted from search queries (query tags) are more appropriate.} }

%0 = techreport %A = Antonellis, Ioannis and Karim, Jawed and Garcia-Molina, Hector %D = 2011 %I = Stanford InfoLab %T = Navigating the Web with Query Tags %U = http://ilpubs.stanford.edu:8090/943/

@article{gasevic2011approach, author = {Gasevic, Dragan and Zouaq, Amal and Torniai, Carlo and Jovanovic, Jelena and Hatala, Marek}, title = {An Approach to Folksonomy-based Ontology Maintenance for Learning Environments}, journal = {IEEE Transactions on Learning Technologies}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, year = {2011}, volume = {99}, number = {1}, url = {http://www.computer.org/portal/web/csdl/doi/10.1109/TLT.2011.21}, doi = {10.1109/TLT.2011.21}, issn = {1939-1382}, keywords = {folksonomy, maintenance, ontology, tags} }

%0 = article %A = Gasevic, Dragan and Zouaq, Amal and Torniai, Carlo and Jovanovic, Jelena and Hatala, Marek %C = Los Alamitos, CA, USA %D = 2011 %I = IEEE Computer Society %T = An Approach to Folksonomy-based Ontology Maintenance for Learning Environments %U = http://www.computer.org/portal/web/csdl/doi/10.1109/TLT.2011.21

Qualitative journal evaluation makes use of cumulated content
scriptions of single articles. These can either be represented by
thor-generated keywords, professionally indexed subject
adings, automatically extracted terms or by reader-generated
gs as used in social bookmarking systems. It is assumed that
rticularly the users? view on article content differs significantly
om the authors? or indexers? perspectives. To verify this
sumption, title and abstract terms, author keywords, Inspec
bject headings, KeyWords PlusTM and tags are compared by
lculating the overlap between the respective datasets. Our
proach includes extensive term preprocessing (i.e. stemming,
elling unifications) to gain a homogeneous term collection.
en term overlap is calculated for every single document of the
taset, similarity values are low. Thus, the presented study
nfirms the assumption, that the different types of keywords
ch reflect a different perspective of the articles? contents and
at tags (cumulated across articles) can be used in journal
aluation to represent a reader-specific view on published
ntent.

@inproceedings{peters2011crowdsourcing, author = {Peters, Isabella and Haustein, Stefanie and Terliesner, Jens}, title = {Crowdsourcing in Article Evaluation}, booktitle = {ACM WebSci'11}, year = {2011}, pages = {1--4}, note = {WebSci Conference 2011}, url = {http://journal.webscience.org/487/}, keywords = {citation, crowd, keywords, tags}, abstract = {Qualitative journal evaluation makes use of cumulated content
scriptions of single articles. These can either be represented by
thor-generated keywords, professionally indexed subject
adings, automatically extracted terms or by reader-generated
gs as used in social bookmarking systems. It is assumed that
rticularly the users? view on article content differs significantly
om the authors? or indexers? perspectives. To verify this
sumption, title and abstract terms, author keywords, Inspec
bject headings, KeyWords PlusTM and tags are compared by
lculating the overlap between the respective datasets. Our
proach includes extensive term preprocessing (i.e. stemming,
elling unifications) to gain a homogeneous term collection.
en term overlap is calculated for every single document of the
taset, similarity values are low. Thus, the presented study
nfirms the assumption, that the different types of keywords
ch reflect a different perspective of the articles? contents and
at tags (cumulated across articles) can be used in journal
aluation to represent a reader-specific view on published
ntent.} }

%0 = inproceedings %A = Peters, Isabella and Haustein, Stefanie and Terliesner, Jens %B = ACM WebSci'11 %D = 2011 %T = Crowdsourcing in Article Evaluation %U = http://journal.webscience.org/487/

We examine the creation of a tag cloud for exploring and understanding a set of objects (e.g., web pages, documents). In the first part of our work, we present a formal system model for reasoning about tag clouds. We then present metrics that capture the structural properties of a tag cloud, and we briefly present a set of tag selection algorithms that are used in current sites (e.g., del.icio.us, Flickr, Technorati) or that have been described in recent work. In order to evaluate the results of these algorithms, we devise a novel synthetic user model. This user model is specifically tailored for tag cloud evaluation and assumes an "ideal" user. We evaluate the algorithms under this user model, as well as the model itself, using two datasets: CourseRank (a Stanford social tool containing information about courses) and del.icio.us (a social bookmarking site). The results yield insights as to when and why certain selection schemes work best.

@inproceedings{venetis2011selection, author = {Venetis, Petros and Koutrika, Georgia and Garcia-Molina, Hector}, title = {On the selection of tags for tag clouds}, booktitle = {Proceedings of the fourth ACM international conference on Web search and data mining}, series = {WSDM '11}, publisher = {ACM}, address = {New York, NY, USA}, year = {2011}, pages = {835--844}, url = {http://doi.acm.org/10.1145/1935826.1935855}, doi = {10.1145/1935826.1935855}, isbn = {978-1-4503-0493-1}, keywords = {selection, tagcloud, tags, toread}, abstract = {We examine the creation of a tag cloud for exploring and understanding a set of objects (e.g., web pages, documents). In the first part of our work, we present a formal system model for reasoning about tag clouds. We then present metrics that capture the structural properties of a tag cloud, and we briefly present a set of tag selection algorithms that are used in current sites (e.g., del.icio.us, Flickr, Technorati) or that have been described in recent work. In order to evaluate the results of these algorithms, we devise a novel synthetic user model. This user model is specifically tailored for tag cloud evaluation and assumes an "ideal" user. We evaluate the algorithms under this user model, as well as the model itself, using two datasets: CourseRank (a Stanford social tool containing information about courses) and del.icio.us (a social bookmarking site). The results yield insights as to when and why certain selection schemes work best.} }

%0 = inproceedings %A = Venetis, Petros and Koutrika, Georgia and Garcia-Molina, Hector %B = Proceedings of the fourth ACM international conference on Web search and data mining %C = New York, NY, USA %D = 2011 %I = ACM %T = On the selection of tags for tag clouds %U = http://doi.acm.org/10.1145/1935826.1935855

Tagging systems are nowadays a common feature in web sites where user-generated content plays an important role. However, the lack of semantics and multilinguality hamper information retrieval process based on folksonomies. In this paper we propose an approach to bring semantics to multilingual folksonomies. This approach includes a sense disambiguation activity and takes advantage from knowledge generated by the masses in the form of articles, redirection and disambiguation links, and translations in Wikipedia. We use DBpedia[2] as semantic resource to define the tag meanings.

@misc{garciasilva2010associating, author = {Garcia-Silva, A. and Corcho, Oscar and Gracia, J.}, title = {Associating Semantics to Multilingual Tags in Folksonomies}, booktitle = {Proceedings of the 17th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2010)}, year = {2010}, url = {http://oa.upm.es/5646/}, keywords = {multilingual, ol_web2.0, semantics, tags, enrichment, tag_concept_mapping}, abstract = {Tagging systems are nowadays a common feature in web sites where user-generated content plays an important role. However, the lack of semantics and multilinguality hamper information retrieval process based on folksonomies. In this paper we propose an approach to bring semantics to multilingual folksonomies. This approach includes a sense disambiguation activity and takes advantage from knowledge generated by the masses in the form of articles, redirection and disambiguation links, and translations in Wikipedia. We use DBpedia[2] as semantic resource to define the tag meanings.} }

%0 = misc %A = Garcia-Silva, A. and Corcho, Oscar and Gracia, J. %B = Proceedings of the 17th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2010) %D = 2010 %T = Associating Semantics to Multilingual Tags in Folksonomies %U = http://oa.upm.es/5646/

@article{gedikli2010rating, author = {Gedikli, Fatih and Jannach, Dietmar}, title = {Rating items by rating tags}, journal = {Systems and the Social Web at ACM }, year = {2010}, keywords = {item, rating, recommender, tags} }

%0 = article %A = Gedikli, Fatih and Jannach, Dietmar %D = 2010 %T = Rating items by rating tags

We investigate tag and query logs to see if the terms people use to annotate websites are similar to the ones they use to query for them. Over a set of URLs, we compare the distribution of tags used to annotate each URL with the distribution of query terms for clicks on the same URL. Understanding the relationship between the distributions is important to determine how useful tag data may be for improving search results and conversely, query data for improving tag prediction. In our study, we compare both term frequency distributions using vocabulary overlap and relative entropy. We also test statistically whether the term counts come from the same underlying distribution. Our results indicate that the vocabulary used for tagging and searching for content are similar but not identical. We further investigate the content of the websites to see which of the two distributions (tag or query) is most similar to the content of the annotated/searched URL. Finally, we analyze the similarity for different categories of URLs in our sample to see if the similarity between distributions is dependent on the topic of the website or the popularity of the URL.

@inproceedings{carman2009statistical, author = {Carman, Mark J. and Baillie, Mark and Gwadera, Robert and Crestani, Fabio}, title = {A statistical comparison of tag and query logs}, booktitle = {Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval}, series = {SIGIR '09}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, pages = {123--130}, url = {http://doi.acm.org/10.1145/1571941.1571965}, doi = {10.1145/1571941.1571965}, isbn = {978-1-60558-483-6}, keywords = {comparison, diagram, divergence, kullblack-Leibler, mining, tags, triangular, vocabulary, weblog}, abstract = {We investigate tag and query logs to see if the terms people use to annotate websites are similar to the ones they use to query for them. Over a set of URLs, we compare the distribution of tags used to annotate each URL with the distribution of query terms for clicks on the same URL. Understanding the relationship between the distributions is important to determine how useful tag data may be for improving search results and conversely, query data for improving tag prediction. In our study, we compare both term frequency distributions using vocabulary overlap and relative entropy. We also test statistically whether the term counts come from the same underlying distribution. Our results indicate that the vocabulary used for tagging and searching for content are similar but not identical. We further investigate the content of the websites to see which of the two distributions (tag or query) is most similar to the content of the annotated/searched URL. Finally, we analyze the similarity for different categories of URLs in our sample to see if the similarity between distributions is dependent on the topic of the website or the popularity of the URL.} }

%0 = inproceedings %A = Carman, Mark J. and Baillie, Mark and Gwadera, Robert and Crestani, Fabio %B = Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval %C = New York, NY, USA %D = 2009 %I = ACM %T = A statistical comparison of tag and query logs %U = http://doi.acm.org/10.1145/1571941.1571965

Under social tagging systems, a typical Web 2.0 application, users label digital data sources by using freely chosen textual descriptions (tags). Poor retrieval in the aforementioned systems remains a major problem mostly due to questionable tag validity and tag ambiguity. Earlier clustering techniques have shown limited improvements, since they were based mostly on tag co-occurrences. In this paper, a co-clustering approach is employed, that exploits joint groups of related tags and social data sources, in which both social and semantic aspects of tags are considered simultaneously. Experimental results demonstrate the efficiency and the beneficial outcome of the proposed approach in correlating relevant tags and resources.

@inproceedings{giannakidou2008coclustering, author = {Giannakidou, Eirini and Koutsonikola, Vassiliki A. and Vakali, Athena and Kompatsiaris, Yiannis}, title = {Co-Clustering Tags and Social Data Sources.}, booktitle = {WAIM}, publisher = {IEEE}, year = {2008}, pages = {317-324}, url = {http://dblp.uni-trier.de/db/conf/waim/waim2008.html#GiannakidouKVK08}, isbn = {978-0-7695-3185-4}, keywords = {clustering, ol_web2.0, tags, methods_concepts}, abstract = {Under social tagging systems, a typical Web 2.0 application, users label digital data sources by using freely chosen textual descriptions (tags). Poor retrieval in the aforementioned systems remains a major problem mostly due to questionable tag validity and tag ambiguity. Earlier clustering techniques have shown limited improvements, since they were based mostly on tag co-occurrences. In this paper, a co-clustering approach is employed, that exploits joint groups of related tags and social data sources, in which both social and semantic aspects of tags are considered simultaneously. Experimental results demonstrate the efficiency and the beneficial outcome of the proposed approach in correlating relevant tags and resources.} }

%0 = inproceedings %A = Giannakidou, Eirini and Koutsonikola, Vassiliki A. and Vakali, Athena and Kompatsiaris, Yiannis %B = WAIM %D = 2008 %I = IEEE %T = Co-Clustering Tags and Social Data Sources. %U = http://dblp.uni-trier.de/db/conf/waim/waim2008.html#GiannakidouKVK08

The quality of the current tagging services can be greatly improved if the service is able to cluster tags by their meaning. Tag clouds clustered by higher level topics enable the users to explore their tag space, which is especially needed when tag clouds become large. We demonstrate TagCluster - a tool for automated tag clustering that harnesses knowledge from Wikipedia about semantic relatedness between tags and names of categories to achieve smart clustering. Our approach shows much better quality of clusters compared to the existing techniques that rely on tag co-occurrence analysis in the tagging service.

@inproceedings{grineva2008harnessing, author = {Grineva, Maria and Grinev, Maxim and Turdakov, Denis and Velikhov, Pavel}, title = {Harnessing Wikipedia for Smart Tags Clustering}, booktitle = {Proceedings of the International Workshop on Knowledge Acquisition from the Social Web (KASW2008)}, year = {2008}, keywords = {clustering, ol_web2.0, tags, wikipedia, methods_concepts, data_wikis}, abstract = {The quality of the current tagging services can be greatly improved if the service is able to cluster tags by their meaning. Tag clouds clustered by higher level topics enable the users to explore their tag space, which is especially needed when tag clouds become large. We demonstrate TagCluster - a tool for automated tag clustering that harnesses knowledge from Wikipedia about semantic relatedness between tags and names of categories to achieve smart clustering. Our approach shows much better quality of clusters compared to the existing techniques that rely on tag co-occurrence analysis in the tagging service.} }

%0 = inproceedings %A = Grineva, Maria and Grinev, Maxim and Turdakov, Denis and Velikhov, Pavel %B = Proceedings of the International Workshop on Knowledge Acquisition from the Social Web (KASW2008) %D = 2008 %T = Harnessing Wikipedia for Smart Tags Clustering

@mastersthesis{illig2008machine, author = {Illig, Jens}, title = {Machine Learnability Analysis of Textclassifications in a Social Bookmarking Folksonomy}, school = {University of Kassel}, type = {Bachelor Thesis}, address = {Kassel}, year = {2008}, keywords = {classification, learning, machine, recommendations, recommender, tags} }

%0 = mastersthesis %A = Illig, Jens %C = Kassel %D = 2008 %T = Machine Learnability Analysis of Textclassifications in a Social Bookmarking Folksonomy

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 occurrences. 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.

@article{jaschke2008recommendations, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, title = {Tag recommendations in social bookmarking systems}, journal = {AI Communications}, year = {2008}, volume = {21}, number = {4}, pages = {231--247}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, doi = {10.3233/AIC-2008-0438}, keywords = {recommendation, social_bookmarking, tagging, tags}, 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 occurrences. 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.} }

%0 = article %A = Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd %D = 2008 %T = Tag recommendations in social bookmarking systems %U = http://dx.doi.org/10.3233/AIC-2008-0438

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.
this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of
er-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.

@article{jaeschke2008tag, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, title = {Tag Recommendations in Social Bookmarking Systems}, editor = {Giunchiglia, Enrico}, journal = {AI Communications}, publisher = {IOS Press}, address = {Amsterdam}, year = {2008}, volume = {21}, number = {4}, pages = {231-247}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, doi = {10.3233/AIC-2008-0438}, issn = {0921-7126}, keywords = {2.0, 2008, Recommendations, bookmarking, itegpub, logsonomies, myown, recommendations, recommender, social, systems, tag, tagorapub, tags, web, web2.0, web20}, 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. } }

%0 = article %A = Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd %C = Amsterdam %D = 2008 %I = IOS Press %T = Tag Recommendations in Social Bookmarking Systems %U = http://dx.doi.org/10.3233/AIC-2008-0438

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.
this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of
er-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.

@article{jaeschke2008tag, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, title = {Tag Recommendations in Social Bookmarking Systems}, editor = {Giunchiglia, Enrico}, journal = {AI Communications}, publisher = {IOS Press}, address = {Amsterdam}, year = {2008}, volume = {21}, number = {4}, pages = {231-247}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, doi = {10.3233/AIC-2008-0438}, issn = {0921-7126}, keywords = {2.0, 2008, Recommendations, bookmarking, itegpub, logsonomies, myown, recommendations, recommender, social, systems, tag, tagorapub, tags, web, web2.0, web20}, 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 ofuser-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.} }

%0 = article %A = Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd %C = Amsterdam %D = 2008 %I = IOS Press %T = Tag Recommendations in Social Bookmarking Systems %U = http://dx.doi.org/10.3233/AIC-2008-0438

The recent evolution of the Web, now designated by the term Web 2.0, has seen the appearance of a huge number of resources created and annotated by users. However the annotations consist only in simple tags that are gathered in unstructured sets called folksonomies. The use of more complex languages to annotate resources and to define semantics according to the vision of the Semantic Web, would improve the understanding by machines and programs, like search engines, of what is on the Web. Indeed tags expressivity is very low compared to the representation standards of the Semantic Web, like RDF and OWL. But users appear to be still reluctant to annotate resources with RDF, and it should be recognized that Semantic Web, contrary to Web 2.0, is still not a reality of today’s Web. One way to take advantage of Semantic Web capabilities right now, without waiting for a change of the annotation usages, would be to be able to generate RDF annotations from tags. As a first step toward this direction, this paper presents a tentative to automatically convert a set of tags into a RDF description in the context of photos on Flickr. Such a method exploits some specificity of tags used on Flickr, some basic natural language processing tools and some semantic resources, in order to relate semantically tags describing a given photo and build a pertinent RDF annotation for this photo.

@article{maala2008conversion, author = {Maala, Mohamed Zied and Delteil, Alexandre and Azough, Ahmed}, title = {A conversion process from Flickr tags to RDF descriptions}, journal = {IADIS INTERNATIONAL JOURNAL ON WWW/INTERNET}, year = {2008}, volume = {6}, number = {1}, url = {http://liris.cnrs.fr/publis/?id=4425}, issn = {1645-7641}, keywords = {conversion, ol_web2.0, rdf, tags, tag_concept_mapping}, abstract = {The recent evolution of the Web, now designated by the term Web 2.0, has seen the appearance of a huge number of resources created and annotated by users. However the annotations consist only in simple tags that are gathered in unstructured sets called folksonomies. The use of more complex languages to annotate resources and to define semantics according to the vision of the Semantic Web, would improve the understanding by machines and programs, like search engines, of what is on the Web. Indeed tags expressivity is very low compared to the representation standards of the Semantic Web, like RDF and OWL. But users appear to be still reluctant to annotate resources with RDF, and it should be recognized that Semantic Web, contrary to Web 2.0, is still not a reality of today’s Web. One way to take advantage of Semantic Web capabilities right now, without waiting for a change of the annotation usages, would be to be able to generate RDF annotations from tags. As a first step toward this direction, this paper presents a tentative to automatically convert a set of tags into a RDF description in the context of photos on Flickr. Such a method exploits some specificity of tags used on Flickr, some basic natural language processing tools and some semantic resources, in order to relate semantically tags describing a given photo and build a pertinent RDF annotation for this photo.} }

%0 = article %A = Maala, Mohamed Zied and Delteil, Alexandre and Azough, Ahmed %D = 2008 %T = A conversion process from Flickr tags to RDF descriptions %U = http://liris.cnrs.fr/publis/?id=4425

@inproceedings{alkhalifa2007towards, author = {Al-Khalifa, Hend S. and Davis, Hugh C.}, title = {Towards better understanding of folksonomic patterns}, booktitle = {Proceedings of the eighteenth conference on Hypertext and hypermedia}, series = {HT '07}, publisher = {ACM}, address = {New York, NY, USA}, year = {2007}, pages = {163--166}, url = {http://doi.acm.org/10.1145/1286240.1286288}, doi = {http://doi.acm.org/10.1145/1286240.1286288}, isbn = {978-1-59593-820-6}, keywords = {analysis, tagging, tags} }

%0 = inproceedings %A = Al-Khalifa, Hend S. and Davis, Hugh C. %B = Proceedings of the eighteenth conference on Hypertext and hypermedia %C = New York, NY, USA %D = 2007 %I = ACM %T = Towards better understanding of folksonomic patterns %U = http://doi.acm.org/10.1145/1286240.1286288

Semantic Metadata, which describes the meaning of documents, can be produced either manually or else semi-automatically using information extraction techniques. Manual techniques are expensive if they rely on skilled cataloguers, but a possible alternative is to make use of community produced annotations such as those collected in folksonomies. This paper reports on an experiment that we carried out to validate the assumption that folksonomies contain higher semantic value than keywords extracted by machines. The experiment has been carried-out in two ways: subjectively, by asking a human indexer to evaluate the quality of the generated keywords from both systems; and automatically, by measuring the percentage of overlap between the folksonomy set and machine generated keywords set. The result of the experiment can be considered as evidence for the rich semantics of folksonomies, demonstrating that folksonomies used in the del.icio.us bookmarking service can be used in the process of generating semantic metadata to annotate web resources.

@article{alkhalifa2006folksonomies, author = {Al-Khalifa, Hend S. and Davis, Hugh C.}, title = {Folksonomies versus Automatic Keyword Extraction: An Empirical Study}, editor = {Isaías, Pedro and Paprzycki, Marcin}, journal = {IADIS INTERNATIONAL JOURNAL ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (IJCSIS)}, publisher = {IADIS ? International Association for Development of the Information Society}, year = {2006}, volume = {Vol. 1}, number = {Number}, pages = {132--143}, url = {http://eprints.ecs.soton.ac.uk/13155/}, keywords = {comparison, folksonomies, keywords, ol_web2.0, study, tags, emergent_semantics}, abstract = {Semantic Metadata, which describes the meaning of documents, can be produced either manually or else semi-automatically using information extraction techniques. Manual techniques are expensive if they rely on skilled cataloguers, but a possible alternative is to make use of community produced annotations such as those collected in folksonomies. This paper reports on an experiment that we carried out to validate the assumption that folksonomies contain higher semantic value than keywords extracted by machines. The experiment has been carried-out in two ways: subjectively, by asking a human indexer to evaluate the quality of the generated keywords from both systems; and automatically, by measuring the percentage of overlap between the folksonomy set and machine generated keywords set. The result of the experiment can be considered as evidence for the rich semantics of folksonomies, demonstrating that folksonomies used in the del.icio.us bookmarking service can be used in the process of generating semantic metadata to annotate web resources.} }

%0 = article %A = Al-Khalifa, Hend S. and Davis, Hugh C. %D = 2006 %I = IADIS ? International Association for Development of the Information Society %T = Folksonomies versus Automatic Keyword Extraction: An Empirical Study %U = http://eprints.ecs.soton.ac.uk/13155/

@inproceedings{citeulike:688160, author = {Dubinko, Micah and Kumar, Ravi and Magnani, Joseph and Novak, Jasmine and Raghavan, Prabhakar and Tomkins, Andrew}, title = {Visualizing tags over time}, booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web}, publisher = {ACM Press}, address = {New York, NY, USA}, year = {2006}, pages = {193--202}, url = {http://dx.doi.org/10.1145/1135777.1135810}, doi = {10.1145/1135777.1135810}, isbn = {1595933239}, keywords = {folksonomy, tagging, tags, time, visualization, visualizing} }

%0 = inproceedings %A = Dubinko, Micah and Kumar, Ravi and Magnani, Joseph and Novak, Jasmine and Raghavan, Prabhakar and Tomkins, Andrew %B = WWW '06: Proceedings of the 15th international conference on World Wide Web %C = New York, NY, USA %D = 2006 %I = ACM Press %T = Visualizing tags over time %U = http://dx.doi.org/10.1145/1135777.1135810

Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs and other content. In this paper we analyze the structure of collaborative tagging systems as well as their dynamic aspects. Specifically, we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given URL. We also present a dynamic model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.

@article{golder2006usage, author = {Golder, Scott A. and Huberman, Bernardo A.}, title = {Usage patterns of collaborative tagging systems}, journal = {Journal of Information Science}, year = {2006}, volume = {32}, number = {2}, pages = {198-208}, url = {http://jis.sagepub.com/content/32/2/198.abstract}, doi = {10.1177/0165551506062337}, keywords = {golder, patterns, tagging, tags, usage}, abstract = {Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs and other content. In this paper we analyze the structure of collaborative tagging systems as well as their dynamic aspects. Specifically, we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given URL. We also present a dynamic model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.} }

%0 = article %A = Golder, Scott A. and Huberman, Bernardo A. %D = 2006 %T = Usage patterns of collaborative tagging systems %U = http://jis.sagepub.com/content/32/2/198.abstract

Immer mehr Soziale-Lesezeichen-Systeme entstehen im heutigen Web. In solchen Systemen erstellen die Nutzer leichtgewichtige begriffliche Strukturen, so genannte Folksonomies. Ihren Erfolg verdanken sie der Tatsache, dass man keine speziellen Fähigkeiten benötigt, um an der Gestaltung mitzuwirken. In diesem Artikel beschreiben wir unser System BibSonomy. Es erlaubt das Speichern, Verwalten und Austauschen sowohl von Lesezeichen (Bookmarks) als auch von Literaturreferenzen in Form von BibTeX-Einträgen. Die Entwicklung des verwendeten Vokabulars und der damit einhergehenden Entstehung einer gemeinsamen Semantik wird detailliert diskutiert.

@inproceedings{hotho2006das, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, title = {Das Entstehen von Semantik in BibSonomy}, booktitle = {Social Software in der Wertschöpfung}, publisher = {Nomos}, address = {Baden-Baden}, year = {2006}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006entstehen.pdf}, keywords = {tags, semantik, 2006, pagerank, tagging, association, hotho, bibsonomy, schmitz, jaeschke, rules, semantics, stumme, BibSonomy, nepomuk, folksonomy, tagorapub, folksonomies, tagora, folkrank, UniK, ol_web2.0, emergentsemantics_evidence}, abstract = {Immer mehr Soziale-Lesezeichen-Systeme entstehen im heutigen Web. In solchen Systemen erstellen die Nutzer leichtgewichtige begriffliche Strukturen, so genannte Folksonomies. Ihren Erfolg verdanken sie der Tatsache, dass man keine speziellen Fähigkeiten benötigt, um an der Gestaltung mitzuwirken. In diesem Artikel beschreiben wir unser System BibSonomy. Es erlaubt das Speichern, Verwalten und Austauschen sowohl von Lesezeichen (Bookmarks) als auch von Literaturreferenzen in Form von BibTeX-Einträgen. Die Entwicklung des verwendeten Vokabulars und der damit einhergehenden Entstehung einer gemeinsamen Semantik wird detailliert diskutiert.} }

%0 = inproceedings %A = Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd %B = Social Software in der Wertschöpfung %C = Baden-Baden %D = 2006 %I = Nomos %T = Das Entstehen von Semantik in BibSonomy %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006entstehen.pdf