@incollection{lorince2015analysis, abstract = {In collaborative tagging systems, it is generally assumed that users assign tags to facilitate retrieval of content at a later time. There is, however, little behavioral evidence that tags actually serve this purpose. Using a large-scale dataset from the social music website Last.fm, we explore how patterns of music tagging and subsequent listening interact to determine if there exist measurable signals of tags functioning as retrieval aids. Specifically, we describe our methods for testing if the assignment of a tag tends to lead to an increase in listening behavior. Results suggest that tagging, on average, leads to only very small increases in listening rates, and overall the data do }, author = {Lorince, Jared and Joseph, Kenneth and Todd, PeterM.}, booktitle = {Social Computing, Behavioral-Cultural Modeling, and Prediction}, doi = {10.1007/978-3-319-16268-3_15}, editor = {Agarwal, Nitin and Xu, Kevin and Osgood, Nathaniel}, interhash = {b6f817ca50d1c44886c9ed58facbf592}, intrahash = {1485f6521c6ae2db520d1a7c3c429f07}, isbn = {978-3-319-16267-6}, language = {English}, pages = {141-152}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, title = {Analysis of Music Tagging and Listening Patterns: Do Tags Really Function as Retrieval Aids?}, url = {http://dx.doi.org/10.1007/978-3-319-16268-3_15}, volume = 9021, year = 2015 } @inproceedings{lorince2014supertagger, author = {Lorince, Jared and Zorowitz, Sam and Murdock, Jaimie and Todd, Peter}, interhash = {4af29810e9c882dc18f560527c65de2f}, intrahash = {014abc7dc30e38859c5e8605dce1a8f6}, title = {“Supertagger” Behavior in Building Folksonomies}, year = 2014 } @inproceedings{heckner2009personal, address = {San Jose, CA, USA}, author = {Heckner, Markus and Heilemann, Michael and Wolff, Christian}, booktitle = {Int'l AAAI Conference on Weblogs and Social Media (ICWSM)}, interhash = {f954e699dc6ca2d0abbe5f6ebe166dc7}, intrahash = {d1074484ea350ad88400fe4fc6984874}, month = may, title = {Personal Information Management vs. Resource Sharing: Towards a Model of Information Behaviour in Social Tagging Systems}, year = 2009 } @techreport{doerfel2014course, abstract = {Social tagging systems have established themselves as an important part in today's web and have attracted the interest from our research community in a variety of investigations. The overall vision of our community is that simply through interactions with the system, i.e., through tagging and sharing of resources, users would contribute to building useful semantic structures as well as resource indexes using uncontrolled vocabulary not only due to the easy-to-use mechanics. Henceforth, a variety of assumptions about social tagging systems have emerged, yet testing them has been difficult due to the absence of suitable data. In this work we thoroughly investigate three available assumptions - e.g., is a tagging system really social? - by examining live log data gathered from the real-world public social tagging system BibSonomy. Our empirical results indicate that while some of these assumptions hold to a certain extent, other assumptions need to be reflected and viewed in a very critical light. Our observations have implications for the design of future search and other algorithms to better reflect the actual user behavior.}, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, interhash = {65f287480af20fc407f7d26677f17b72}, intrahash = {e360f0bd207806e72305efe16491ebe3}, note = {cite arxiv:1401.0629}, title = {Of course we share! Testing Assumptions about Social Tagging Systems}, url = {http://arxiv.org/abs/1401.0629}, year = 2014 } @article{landia2013deeper, abstract = {The information contained in social tagging systems is often modelled as a graph of connections between users, items and tags. Recommendation algorithms such as FolkRank, have the potential to leverage complex relationships in the data, corresponding to multiple hops in the graph. We present an in-depth analysis and evaluation of graph models for social tagging data and propose novel adaptations and extensions of FolkRank to improve tag recommendations. We highlight implicit assumptions made by the widely used folksonomy model, and propose an alternative and more accurate graph-representation of the data. Our extensions of FolkRank address the new item problem by incorporating content data into the algorithm, and significantly improve prediction results on unpruned datasets. Our adaptations address issues in the iterative weight spreading calculation that potentially hinder FolkRank's ability to leverage the deep graph as an information source. Moreover, we evaluate the benefit of considering each deeper level of the graph, and present important insights regarding the characteristics of social tagging data in general. Our results suggest that the base assumption made by conventional weight propagation methods, that closeness in the graph always implies a positive relationship, does not hold for the social tagging domain.}, author = {Landia, Nikolas and Doerfel, Stephan and Jäschke, Robert and Anand, Sarabjot Singh and Hotho, Andreas and Griffiths, Nathan}, interhash = {e8095b13630452ce3ecbae582f32f4bc}, intrahash = {e585a92994be476480545eb62d741642}, journal = {cs.IR}, title = {Deeper Into the Folksonomy Graph: FolkRank Adaptations and Extensions for Improved Tag Recommendations}, url = {http://arxiv.org/abs/1310.1498}, volume = {1310.1498}, year = 2013 } @inproceedings{mueller2013recommendations, abstract = {With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.}, author = {Mueller, Juergen and Doerfel, Stephan and Becker, Martin and Hotho, Andreas and Stumme, Gerd}, booktitle = {Recommender Systems and the Social Web Workshop at 7th ACM Conference on Recommender Systems, RecSys 2013, Hong Kong, China -- October 12-16, 2013. Proceedings}, interhash = {23d1cf49208d9a0c8b883dc69d4e444d}, intrahash = {6190d6064dfdb3b8d71f2898539e993e}, note = {accepted for publication}, pages = {New York, NY, USA}, publisher = {ACM}, title = {Tag Recommendations for SensorFolkSonomies}, year = 2013 } @inproceedings{abrams1998information, acmid = {274651}, address = {New York, NY, USA}, author = {Abrams, David and Baecker, Ron and Chignell, Mark}, booktitle = {Proceedings of the SIGCHI Conference on Human Factors in Computing Systems}, doi = {10.1145/274644.274651}, interhash = {fbb2704604de0954b432c8615a0abf5b}, intrahash = {a9a25a144cec844bcd7daeace4a548aa}, isbn = {0-201-30987-4}, location = {Los Angeles, California, USA}, numpages = {8}, pages = {41--48}, publisher = {ACM Press/Addison-Wesley Publishing Co.}, series = {CHI '98}, title = {Information archiving with bookmarks: personal Web space construction and organization}, url = {http://dx.doi.org/10.1145/274644.274651}, year = 1998 } @inproceedings{dominguezgarcia2012freset, abstract = {FReSET is a new recommender systems evaluation framework aiming to support research on folksonomy-based recommender systems. It provides interfaces for the implementation of folksonomy-based recommender systems and supports the consistent and reproducible offline evaluations on historical data. Unlike other recommender systems framework projects, the emphasis here is on providing a flexible framework allowing users to implement their own folksonomy-based recommender algorithms and pre-processing filtering methods rather than just providing a collection of collaborative filtering implementations. FReSET includes a graphical interface for result visualization and different cross-validation implementations to complement the basic functionality.}, acmid = {2365939}, address = {New York, NY, USA}, author = {Dom\'{\i}nguez Garc\'{\i}a, Renato and Bender, Matthias and Anjorin, Mojisola and Rensing, Christoph and Steinmetz, Ralf}, booktitle = {Proceedings of the 4th ACM RecSys workshop on Recommender systems and the social web}, doi = {10.1145/2365934.2365939}, interhash = {489207308b5d7f064163652763794ce6}, intrahash = {c78b033eb1b463ff00c4fc67ed8bf679}, isbn = {978-1-4503-1638-5}, location = {Dublin, Ireland}, numpages = {4}, pages = {25--28}, publisher = {ACM}, series = {RSWeb '12}, title = {FReSET: an evaluation framework for folksonomy-based recommender systems}, url = {http://doi.acm.org/10.1145/2365934.2365939}, year = 2012 } @inproceedings{krause2008logsonomy, 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.}, address = {New York, NY, USA}, author = {Krause, Beate and Jäschke, Robert and Hotho, Andreas and Stumme, Gerd}, booktitle = {HT '08: Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, doi = {http://doi.acm.org/10.1145/1379092.1379123}, interhash = {6d34ea1823d95b9dbf37d4db4d125d2a}, intrahash = {76d81124951ae39060a8bc98f4883435}, isbn = {978-1-59593-985-2}, location = {Pittsburgh, PA, USA}, pages = {157--166}, publisher = {ACM}, title = {Logsonomy - Social Information Retrieval with Logdata}, url = {http://portal.acm.org/citation.cfm?id=1379092.1379123&coll=ACM&dl=ACM&type=series&idx=SERIES399&part=series&WantType=Journals&title=Proceedings%20of%20the%20nineteenth%20ACM%20conference%20on%20Hypertext%20and%20hypermedia}, vgwort = {17}, year = 2008 } @inproceedings{krause2008comparison, abstract = {Social bookmarking systems allow users to store links to internet resources on a web page. As social bookmarking systems are growing in popularity, search algorithms have been developed that transfer the idea of link-based rankings in the Web to a social bookmarking system's data structure. These rankings differ from traditional search engine rankings in that they incorporate the rating of users.

In this study, we compare search in social bookmarking systems with traditionalWeb search. In the first part, we compare the user activity and behaviour in both kinds of systems, as well as the overlap of the underlying sets of URLs. In the second part,we compare graph-based and vector space rankings for social bookmarking systems with commercial search engine rankings.

Our experiments are performed on data of the social bookmarking system Del.icio.us and on rankings and log data from Google, MSN, and AOL. We will show that part of the difference between the systems is due to different behaviour (e. g., the concatenation of multi-word lexems to single terms in Del.icio.us), and that real-world events may trigger similar behaviour in both kinds of systems. We will also show that a graph-based ranking approach on folksonomies yields results that are closer to the rankings of the commercial search engines than vector space retrieval, and that the correlation is high in particular for the domains that are well covered by the social bookmarking system.}, acmid = {1793290}, address = {Berlin, Heidelberg}, author = {Krause, Beate and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the IR research, 30th European conference on Advances in information retrieval}, interhash = {37598733b747093d97a0840a11beebf5}, intrahash = {039ff6ddae0794aceb5ccaecb88e3cb6}, isbn = {3-540-78645-7, 978-3-540-78645-0}, location = {Glasgow, UK}, numpages = {13}, pages = {101--113}, publisher = {Springer-Verlag}, series = {ECIR'08}, title = {A comparison of social bookmarking with traditional search}, url = {http://dl.acm.org/citation.cfm?id=1793274.1793290}, year = 2008 } @inproceedings{wetzker2009hybrid, abstract = {In this paper we consider the problem of item recommendation in collaborative tagging communities, so called folksonomies, where users annotate interesting items with tags. Rather than following a collaborative filtering or annotation-based approach to recommendation, we extend the probabilistic latent semantic analysis (PLSA) approach and present a unified recommendation model which evolves from item user and item tag co-occurrences in parallel. The inclusion of tags reduces known collaborative filtering problems related to overfitting and allows for higher quality recommendations. Experimental results on a large snapshot of the delicious bookmarking service show the scalability of our approach and an improved recommendation quality compared to two-mode collaborative or annotation based methods.}, acmid = {1506255}, address = {New York, NY, USA}, author = {Wetzker, Robert and Umbrath, Winfried and Said, Alan}, booktitle = {Proceedings of the WSDM '09 Workshop on Exploiting Semantic Annotations in Information Retrieval}, doi = {10.1145/1506250.1506255}, interhash = {5a4e686feaa38748f7eac2c8a3afe51e}, intrahash = {733e1968baace40173bd30486b49a8f0}, isbn = {978-1-60558-430-0}, location = {Barcelona, Spain}, numpages = {5}, pages = {25--29}, publisher = {ACM}, series = {ESAIR '09}, title = {A hybrid approach to item recommendation in folksonomies}, url = {http://doi.acm.org/10.1145/1506250.1506255}, year = 2009 } @article{benz2010social, abstract = {Social resource sharing systems are central elements of the Web 2.0 and use the same kind of lightweight knowledge representation, called folksonomy. Their large user communities and ever-growing networks of user-generated content have made them an attractive object of investigation for researchers from different disciplines like Social Network Analysis, Data Mining, Information Retrieval or Knowledge Discovery. In this paper, we summarize and extend our work on different aspects of this branch of Web 2.0 research, demonstrated and evaluated within our own social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind. We structure this presentation along the different interaction phases of a user with our system, coupling the relevant research questions of each phase with the corresponding implementation issues. This approach reveals in a systematic fashion important aspects and results of the broad bandwidth of folksonomy research like capturing of emergent semantics, spam detection, ranking algorithms, analogies to search engine log data, personalized tag recommendations and information extraction techniques. We conclude that when integrating a real-life application like BibSonomy into research, certain constraints have to be considered; but in general, the tight interplay between our scientific work and the running system has made BibSonomy a valuable platform for demonstrating and evaluating Web 2.0 research.}, address = {Berlin / Heidelberg}, author = {Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Mitzlaff, Folke and Schmitz, Christoph and Stumme, Gerd}, doi = {10.1007/s00778-010-0208-4}, interhash = {57fe43734b18909a24bf5bf6608d2a09}, intrahash = {c9437d5ec56ba949f533aeec00f571e3}, issn = {1066-8888}, journal = {The VLDB Journal}, month = dec, number = 6, pages = {849--875}, publisher = {Springer}, title = {The Social Bookmark and Publication Management System BibSonomy}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf}, volume = 19, year = 2010 } @inproceedings{Abel:2008:RFS:1458082.1458316, acmid = {1458316}, address = {New York, NY, USA}, author = {Abel, Fabian and Henze, Nicola and Krause, Daniel}, booktitle = {Proceeding of the 17th ACM conference on Information and knowledge management}, doi = {http://doi.acm.org/10.1145/1458082.1458316}, interhash = {5d6db50409eef97339b135ab8f703538}, intrahash = {f66b82fc919462c25698392c3cf4e6fa}, isbn = {978-1-59593-991-3}, location = {Napa Valley, California, USA}, numpages = {2}, pages = {1429--1430}, publisher = {ACM}, series = {CIKM '08}, title = {Ranking in folksonomy systems: can context help?}, url = {http://doi.acm.org/10.1145/1458082.1458316}, year = 2008 } @misc{Xu09relevanceranking, author = {Xu, Jun and Li, Hang and Zhong, Chaoliang}, interhash = {c0a86e1785768ef1f15d5cacc1442597}, intrahash = {4d086714a580d80c68077fcc98656db3}, title = {Relevance Ranking using Kernels}, url = {http://www.google.de/url?sa=t&source=web&cd=2&ved=0CCEQFjAB&url=http%3A%2F%2Fresearch.microsoft.com%2Fpubs%2F81437%2FMSR_TechReport_2009_Kernel4IR.pdf&rct=j&q=Relevance%20Ranking%20using%20Kernels&ei=uzftTM28GMr2sgaO4Y35Dg&usg=AFQjCNFftCUJMs7LgoqEXR2VvT7bQ7FWHw&sig2=H5OBpauNrYXJ0asAFrEuGQ&cad=rja}, year = 2009 } @article{PeSt08, abstract = {Folksonomies in Wissensrepr{\"a}sentation und Information Retrieval. Die popul{\"a}ren Web 2.0-Dienste werden von Prosumern -- Produzenten und gleichsam Konsumenten -- nicht nur dazu genutzt, Inhalte zu produzieren, sondern auch, um sie inhaltlich zu erschlie{\ss}en. Folksonomies erlauben es dem Nutzer, Dokumente mit eigenen Schlagworten, sog. Tags, zu beschreiben, ohne dabei auf gewisse Regeln oder Vorgaben achten zu m{\"u}ssen. Neben einigen Vorteilen zeigen Folksonomies aber auch zahlreiche Schw{\"a}chen (u. a. einen Mangel an Pr{\"a}zision). Um diesen Nachteilen gr{\"o}{\ss}tenteils entgegenzuwirken, schlagen wir eine Interpretation der Tags als nat{\"u}rlichsprachige W{\"o}rter vor. Dadurch ist es uns m{\"o}glich, Methoden des Natural Language Processing (NLP) auf die Tags anzuwenden und so linguistische Probleme der Tags zu beseitigen. Dar{\"u}ber hinaus diskutieren wir Ans{\"a}tze und weitere Vorschl{\"a}ge (Tagverteilungen, Kollaboration und akteurspezifische Aspekte) hinsichtlich eines Relevance Rankings von getaggten Dokumenten. Neben Vorschl{\"a}gen auf {\"a}hnliche Dokumente ({\glqq}more like this!{\grqq}) erlauben Folksonomies auch Hinweise auf verwandte Nutzer und damit auf Communities ({\glqq}more like me!{\grqq}). Folksonomies in Knowledge Representation and Information Retrieval In Web 2.0 services {\grqq}prosumers” -- producers and consumers -- collaborate not only for the purpose of creating content, but to index these pieces of information as well. Folksonomies permit actors to describe documents with subject headings, {\grqq}tags{\grqq}, without regarding any rules. Apart from a lot of benefits folksonomies have many shortcomings (e.g., lack of precision). In order to solve some of the problems we propose interpreting tags as natural language terms. Accordingly, we can introduce methods of NLP to solve the tags’ linguistic problems. Additionally, we present criteria for tagged documents to create a ranking by relevance (tag distribution, collaboration and actor-based aspects). Besides recommending similar documents ({\glqq}more like this!{\grqq}) folksonomies can be used for the recommendation of similar users and communities ({\glqq}more like me!{\grqq}). }, author = {Peters, Isabella and Stock, Wolfgang G.}, interhash = {93b09c0700650150065232180fb23115}, intrahash = {3abe2759f6837cbd247021cb26bcf760}, issn = {1434-4653}, journal = {Information -- Wissenschaft und Praxis}, localfile = {Wissenschaftliche Bibliothek/dokumente/StPe08.pdf}, number = 2, pages = {77--90}, title = {{Folksonomies in Wissensrepr{\"a}sentation und Information Retrieval}}, url = {http://www.phil-fak.uni-duesseldorf.de/infowiss/admin/public_dateien/files/1/1204547968stock212_h.htm}, volume = {59 }, year = 2008 } @inproceedings{marinho:ecml2009, abstract = {This paper describes our approach to the ECML/PKDD Discovery Challenge 2009. Our approach is a pure statistical model taking no content information into account. It tries to find latent interactions between users, items and tags by factorizing the observed tagging data. The factorization model is learned by the Bayesian Personal Ranking method (BPR) which is inspired by a Bayesian analysis of personalized ranking with missing data. To prevent overfitting, we ensemble the models over several iterations and hyperparameters. Finally, we enhance the top-n lists by estimating how many tags to recommend.}, address = {Bled, Slovenia}, author = {Rendle, Steffen and Schmidt-Thieme, Lars}, booktitle = {ECML PKDD Discovery Challenge 2009 (DC09)}, editor = {Eisterlehner, Folke and Hotho, Andreas and Jäschke, Robert}, interhash = {8485850cde1a6b61971cac27fa867845}, intrahash = {ceed045a84e121fa37384f797306d30f}, issn = {1613-0073}, month = {September}, pages = {235--242}, publisher = {CEUR Workshop Proceedings}, title = {Factor Models for Tag Recommendation in BibSonomy}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-497/}, volume = 497, year = 2009 } @inproceedings{hotho2006bibsonomy, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. The reason for their immediate success is the fact that no specific skills are needed for participating. In this paper we specify a formal model for folksonomies and briefly describe our own system BibSonomy, which allows for sharing both bookmarks and publication references in a kind of personal library.}, address = {Aalborg}, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Proceedings of the First Conceptual Structures Tool Interoperability Workshop at the 14th International Conference on Conceptual Structures}, editor = {de Moor, Aldo and Polovina, Simon and Delugach, Harry}, interhash = {d28c9f535d0f24eadb9d342168836199}, intrahash = {5854a71547051543dd3d3d5e2e2f2b67}, isbn = {87-7307-769-0}, pages = {87-102}, publisher = {Aalborg Universitetsforlag}, title = {{BibSonomy}: A Social Bookmark and Publication Sharing System}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006bibsonomy.pdf}, year = 2006 } @inproceedings{abel_CIKM_2008, abstract = {Folksonomy systems have shown to contribute to the quality of Web search ranking strategies. In this paper, we analyze and compare different graph-based ranking algorithms, namely FolkRank, SocialPageRank, and SocialSimRank. We enhance these algorithms by exploiting the context of tag assignmets, and evaluate the results on the GroupMe! dataset. In GroupMe!, users can organize and maintain arbitrary Web resources in self-defined groups. When users annotate resources in GroupMe!, this can be interpreted in context of a certain group. The grouping activity delivers valuable semantic information about resources and their context. We show how to use this information to improve the detection of relevant search results, and compare different strategies for ranking result lists in folksonomy systems.}, address = {New York, NY, USA}, author = {Abel, Fabian and Henze, Nicola and Krause, Daniel}, booktitle = {CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining}, citeulike-article-id = {3500798}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1458082.1458316}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1458082.1458316}, doi = {10.1145/1458082.1458316}, interhash = {5d6db50409eef97339b135ab8f703538}, intrahash = {d6d72db224fb84c0b4265f09111483e0}, isbn = {978-1-59593-991-3}, location = {Napa Valley, California, USA}, pages = {1429--1430}, posted-at = {2009-12-07 00:16:11}, priority = {2}, publisher = {ACM}, title = {Ranking in folksonomy systems: can context help?}, url = {http://dx.doi.org/10.1145/1458082.1458316}, 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 Marinho, Leandro Balby 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{TM06, author = {Tosic, Milorad and Milicevic, Valentina}, booktitle = {Proc. of the 2nd Workshop on Scripting for the Semantic Web, Colocated with ESWC 2006, Budva, Montenegro}, citeulike-article-id = {2162732}, interhash = {210bbf3d070fb10d1d01383669aac114}, intrahash = {130dca8ecbb764f333199c4e3970f606}, priority = {2}, title = {The Semantics of Collaborative Tagging Systems}, url = {http://www.semanticscripting.org/SFSW2006/Paper6.pdf}, year = 2006 } @inproceedings{citeulike:688160, address = {New York, NY, USA}, author = {Dubinko, Micah and Kumar, Ravi and Magnani, Joseph and Novak, Jasmine and Raghavan, Prabhakar and Tomkins, Andrew}, booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web}, citeulike-article-id = {688160}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1135777.1135810}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1135777.1135810}, doi = {10.1145/1135777.1135810}, interhash = {b9ff2f72831a1406013a86c8202d6276}, intrahash = {cca8a679a78e2bced9a5cc268cfd3aaa}, isbn = {1595933239}, pages = {193--202}, posted-at = {2008-04-27 18:08:29}, priority = {5}, publisher = {ACM Press}, title = {Visualizing tags over time}, url = {http://dx.doi.org/10.1145/1135777.1135810}, year = 2006 } @misc{Lambiotte2005, abstract = { We describe online collaborative communities by tripartite networks, the nodes being persons, items and tags. We introduce projection methods in order to uncover the structures of the networks, i.e. communities of users, genre families... To do so, we focus on the correlations between the nodes, depending on their profiles, and use percolation techniques that consist in removing less correlated links and observing the shaping of disconnected islands. The structuring of the network is visualised by using a tree representation. The notion of diversity in the system is also discussed. }, author = {Lambiotte, R. and Ausloos, M.}, interhash = {7a9dab1c733e8e1982d5f91979749ce9}, intrahash = {65c6f348a54f872fb3e60b4bd64b485b}, note = {cite arxiv:cs.DS/0512090 }, title = {Collaborative tagging as a tripartite network}, url = {http://arxiv.org/abs/cs/0512090}, year = 2005 } @inproceedings{Jiang97taxonomySimilarity, abstract = {This paper presents a new approach for measuring semantic similarity/distance between words and concepts. It combines a lexical taxonomy structure with corpus statistical information so that the semantic distance between nodes in the semantic space constructed by the taxonomy can be better quantified with the computational evidence derived from a distributional analysis of corpus data. Specifically, the proposed measure is a combined approach that inherits the edge-based approach of the edge counting scheme, which is then enhanced by the node-based approach of the information content calculation. When tested on a common data set of word pair similarity ratings, the proposed approach outperforms other computational models. It gives the highest correlation value (r = 0.828) with a benchmark based on human similarity judgements, whereas an upper bound (r = 0.885) is observed when human subjects replicate the same task.}, author = {Jiang, J.J. and Conrath, D.W.}, booktitle = {Proc. of the Int'l. Conf. on Research in Computational Linguistics}, file = {jiang1997ssb.pdf:jiang1997ssb.pdf:PDF}, interhash = {175ec03ee8c47d4b2d0a083609a78e05}, intrahash = {c4ffc507dafc908eab62fde53f7e4f7a}, pages = {19--33}, title = {Semantic similarity based on corpus statistics and lexical taxonomy}, url = {http://www.cse.iitb.ac.in/~cs626-449/Papers/WordSimilarity/4.pdf}, year = 1997 } @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 = {Berlin/Heidelberg}, 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}, 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 = {466f25c93d5e9c13ca5689191ef711ee}, isbn = {978-3-540-88563-4}, pages = {615--631}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Semantic Grounding of Tag Relatedness in Social Bookmarking Systems}, url = {http://cxnets.googlepages.com/cattuto_iswc2008.pdf}, volume = 5318, year = 2008 } @article{april05lund, author = {Lund, Ben and Hammond, Tony and Flack, Martin and Hannay, Timo}, doi = {10.1045/april2005-lund}, interhash = {46c0a98ab6ccb96ff4722f35781807de}, intrahash = {13958ef5da2d2133b9b84e9a3cb40da1}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = {April }, number = 4, title = {Social Bookmarking Tools (II): A Case Study - Connotea}, url = {http://www.dlib.org/dlib/april05/lund/04lund.html}, volume = 11, year = 2005 } @incollection{citeulike:1377860, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. These systems provide currently relatively few structure. We discuss in this paper, how association rule mining can be adopted to analyze and structure folksonomies, and how the results can be used for ontology learning and supporting emergent semantics. We demonstrate our approach on a large scale dataset stemming from an online system.}, author = {Schmitz, Christoph and Hotho, Andreas and J\"{a}schke, Robert and Stumme, Gerd}, citeulike-article-id = {1377860}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-34416-0\_28}, doi = {10.1007/3-540-34416-0\_28}, interhash = {b4a63aa5632ff093c2d345005fa16a17}, intrahash = {06ea55e8751a06c3b44a92543dd6e85a}, journal = {Data Science and Classification}, pages = {261--270}, posted-at = {2008-04-27 16:27:04}, priority = {5}, title = {Mining Association Rules in Folksonomies}, url = {http://dx.doi.org/10.1007/3-540-34416-0\_28}, year = 2006 } @inproceedings{hotho2006emergent, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. The reason for their immediate success is the fact that no specific skills are needed for participating. In this paper we specify a formal model for folksonomies, briefly describe our own system BibSonomy, which allows for sharing both bookmarks and publication references, and discuss first steps towards emergent semantics.}, address = {Bonn}, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Informatik 2006 -- Informatik für Menschen. Band 2}, editor = {Hochberger, Christian and Liskowsky, Rüdiger}, interhash = {53e5677ab0bf1a8f5a635cc32c9082ba}, intrahash = {05043cc20f1e0f5a612135c970e4f1ac}, month = oct, note = {Proc. Workshop on Applications of Semantic Technologies, Informatik 2006}, publisher = {Gesellschaft für Informatik}, series = {Lecture Notes in Informatics}, title = {Emergent Semantics in BibSonomy}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006emergent.pdf}, volume = {P-94}, year = 2006 } @misc{citeulike:305755, 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 dynamical 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 dynamical model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.}, author = {Golder, Scott and Huberman, Bernardo A.}, citeulike-article-id = {305755}, eprint = {cs.DL/0508082}, interhash = {2d312240f16eba52c5d73332bc868b95}, intrahash = {f852d7a909fa3edceb04abb7d2a20f71}, month = Aug, title = {The Structure of Collaborative Tagging Systems}, url = {http://arxiv.org/abs/cs.DL/0508082}, year = 2005 } @article{cattuto2007network, author = {Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd}, editor = {Hoche, Susanne and Nürnberger, Andreas and Flach, Jürgen}, interhash = {fc5f2df61d28bc99b7e15029da125588}, intrahash = {da6c676c5664017247c7564fc247b190}, issn = {0921-7126}, journal = {AI Communications Journal, Special Issue on ``Network Analysis in Natural Sciences and Engineering''}, number = 4, pages = {245-262}, publisher = {IOS Press}, title = {Network Properties of Folksonomies}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2007/cattuto2007network.pdf}, vgwort = {67}, volume = 20, year = 2007 } @inproceedings{Ahn07snowballSampling, abstract = {Social networking services are a fast-growing business in the Internet. However, it is unknown if online relationships and their growth patterns are the same as in real-life social networks. In this paper, we compare the structures of three online social networking services: Cyworld, MySpace, and orkut, each with more than 10 million users, respectively. We have access to complete data of Cyworld's ilchon (friend) relationships and analyze its degree distribution, clustering property, degree correlation, and evolution over time. We also use Cyworld data to evaluate the validity of snowball sampling method, which we use to crawl and obtain partial network topologies of MySpace and orkut. Cyworld, the oldest of the three, demonstrates a changing scaling behavior over time in degree distribution. The latest Cyworld data's degree distribution exhibits a multi-scaling behavior, while those of MySpace and orkut have simple scaling behaviors with different exponents. Very interestingly, each of the two e ponents corresponds to the different segments in Cyworld's degree distribution. Certain online social networking services encourage online activities that cannot be easily copied in real life; we show that they deviate from close-knit online social networks which show a similar degree correlation pattern to real-life social networks.}, address = {New York, NY, USA}, author = {Ahn, Yong-Yeol and Han, Seungyeop and Kwak, Haewoon and Moon, Sue and Jeong, Hawoong}, booktitle = {WWW '07: Proceedings of the 16th international conference on World Wide Web}, doi = {http://doi.acm.org/10.1145/1242572.1242685}, interhash = {444ffef9e7a5b4255d78f26f0409864d}, intrahash = {6165fcf297f7b8cca2f9bb7e73c7d890}, isbn = {978-1-59593-654-7}, location = {Banff, Alberta, Canada}, pages = {835--844}, publisher = {ACM}, title = {Analysis of topological characteristics of huge online social networking services}, url = {http://portal.acm.org/citation.cfm?id=1242685}, year = 2007 } @misc{Cattuto2006, abstract = { Collaborative tagging has been quickly gaining ground because of its ability to recruit the activity of web users into effectively organizing and sharing vast amounts of information. Here we collect data from a popular system and investigate the statistical properties of tag co-occurrence. We introduce a stochastic model of user behavior embodying two main aspects of collaborative tagging: (i) a frequency-bias mechanism related to the idea that users are exposed to each other's tagging activity; (ii) a notion of memory - or aging of resources - in the form of a heavy-tailed access to the past state of the system. Remarkably, our simple modeling is able to account quantitatively for the observed experimental features, with a surprisingly high accuracy. This points in the direction of a universal behavior of users, who - despite the complexity of their own cognitive processes and the uncoordinated and selfish nature of their tagging activity - appear to follow simple activity patterns. }, author = {Cattuto, Ciro and Loreto, Vittorio and Pietronero, Luciano}, interhash = {59b1bd0ed96f41d2c3c98ff232df5dd2}, intrahash = {8d265ea13915a79ec08fe13b8e7074c7}, note = {cite arxiv:cs/0605015 Comment: 8 pages, 7 figures}, title = {Collaborative Tagging and Semiotic Dynamics}, url = {http://arxiv.org/abs/cs/0605015}, year = 2006 } @inproceedings{hotho06trend, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Proc. First International Conference on Semantics And Digital Media Technology (SAMT)}, date = {2006-12-13}, editor = {Avrithis, Yannis S. and Kompatsiaris, Yiannis and Staab, Steffen and O'Connor, Noel E.}, ee = {http://dx.doi.org/10.1007/11930334_5}, interhash = {227be738c5cea57530d592463fd09abd}, intrahash = {2df7426d8ae0bd65c6f095d3fc8a703e}, isbn = {3-540-49335-2}, pages = {56-70}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Trend Detection in Folksonomies}, url = {http://dblp.uni-trier.de/db/conf/samt/samt2006.html#HothoJSS06}, vgwort = {27}, volume = 4306, year = 2006 } @inproceedings{hotho2006information, address = {Budva, Montenegro}, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Proceedings of the 3rd European Semantic Web Conference }, interhash = {10ec64d80b0ac085328a953bb494fb89}, intrahash = {7da1127fc4836e2cf58e3073f1b888b2}, isbn = {3-540-34544-2}, month = {June}, pages = {411-426}, publisher = {Springer}, series = {LNCS}, title = {Information Retrieval in Folksonomies: Search and Ranking}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/seach2006hotho_eswc.pdf}, vgwort = {29}, volume = 4011, year = 2006 } @inproceedings{mika2005ontologies, abstract = {In our work we extend the traditional bipartite model of ontologies with the social dimension, leading to a tripartite model of actors, concepts and instances. We demonstrate the application of this representation by showing how community-based semantics emerges from this model through a process of graph transformation. We illustrate ontology emergence by two case studies, an analysis of a large scale folksonomy system and a novel method for the extraction of community-based ontologies...}, author = {Mika, Peter}, booktitle = {International Semantic Web Conference}, citeulike-article-id = {1020245}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.2861}, interhash = {5ea12110b5bb0e3a8ad09aeb16a70cdb}, intrahash = {399364f1c39abf3efcc19cb0de12f40c}, month = {November}, organization = {International Semantic Web Conference 2005}, pages = {522--536}, posted-at = {2008-04-27 15:43:44}, priority = {5}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Ontologies Are Us: A unified model of social networks and semantics}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.2861}, volume = 3729, year = 2005 } @inproceedings{jaeschke2009testing, abstract = {The challenge to provide tag recommendations for collaborative tagging systems has attracted quite some attention of researchers lately. However, most research focused on the evaluation and development of appropriate methods rather than tackling the practical challenges of how to integrate recommendation methods into real tagging systems, record and evaluate their performance. In this paper we describe the tag recommendation framework we developed for our social bookmark and publication sharing system 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. Furthermore, this paper presents a �rst evaluation of two exemplarily deployed recommendation methods.}, address = {New York, NY, USA}, author = {Jäschke, Robert and Eisterlehner, Folke and Hotho, Andreas and Stumme, Gerd}, booktitle = {RecSys '09: Proceedings of the 2009 ACM Conference on Recommender Systems}, interhash = {440fafda1eccf4036066f457eb6674a0}, intrahash = {1320904b208d53bd5d49e751cbfcc268}, location = {New York, NY, USA}, note = {(to appear)}, publisher = {ACM}, title = {Testing and Evaluating Tag Recommenders in a Live System}, year = 2009 }