@inproceedings{angelova2008characterizing, abstract = {Social networks and collaborative tagging systems are rapidly gaining popularity as a primary means for storing and sharing data among friends, family, colleagues, or perfect strangers as long as they have common interests. del.icio.us is a social network where people store and share their personal bookmarks. Most importantly, users tag their bookmarks for ease of information dissemination and later look up. However, it is the friendship links, that make delicious a social network. They exist independently of the set of bookmarks that belong to the users and have no relation to the tags typically assigned to the bookmarks. To study the interaction among users, the strength of the existing links and their hidden meaning, we introduce implicit links in the network. These links connect only highly "similar" users. Here, similarity can reflect different aspects of the user’s profile that makes her similar to any other user, such as number of shared bookmarks, or similarity of their tags clouds. We investigate the question whether friends have common interests, we gain additional insights on the strategies that users use to assign tags to their bookmarks, and we demonstrate that the graphs formed by implicit links have unique properties differing from binomial random graphs or random graphs with an expected power-law degree distribution. }, author = {Angelova, Ralitsa and Lipczak, Marek and Milios, Evangelos and Prałat, Paweł}, booktitle = {Proceedings of the Mining Social Data Workshop (MSoDa)}, interhash = {f74d27a66d2754f3d5892d68c4abee4c}, intrahash = {02d6739886a13180dd92fbb7243ab58b}, month = jul, organization = {ECAI 2008}, pages = {21--25}, title = {Characterizing a social bookmarking and tagging network}, url = {http://www.math.ryerson.ca/~pralat/papers/2008_delicious.pdf}, year = 2008 } @inproceedings{rendle2010pairwise, abstract = {Tagging plays an important role in many recent websites. Recommender systems can help to suggest a user the tags he might want to use for tagging a specific item. Factorization models based on the Tucker Decomposition (TD) model have been shown to provide high quality tag recommendations outperforming other approaches like PageRank, FolkRank, collaborative filtering, etc. The problem with TD models is the cubic core tensor resulting in a cubic runtime in the factorization dimension for prediction and learning.

In this paper, we present the factorization model PITF (Pairwise Interaction Tensor Factorization) which is a special case of the TD model with linear runtime both for learning and prediction. PITF explicitly models the pairwise interactions between users, items and tags. The model is learned with an adaption of the Bayesian personalized ranking (BPR) criterion which originally has been introduced for item recommendation. Empirically, we show on real world datasets that this model outperforms TD largely in runtime and even can achieve better prediction quality. Besides our lab experiments, PITF has also won the ECML/PKDD Discovery Challenge 2009 for graph-based tag recommendation.}, acmid = {1718498}, address = {New York, NY, USA}, author = {Rendle, Steffen and Schmidt-Thieme, Lars}, booktitle = {Proceedings of the third ACM international conference on Web search and data mining}, doi = {10.1145/1718487.1718498}, interhash = {ce8fbdf2afb954579cdb58104fb683a7}, intrahash = {10fe730b391b08031f3103f9cdbb6e1a}, isbn = {978-1-60558-889-6}, location = {New York, New York, USA}, numpages = {10}, pages = {81--90}, publisher = {ACM}, title = {Pairwise interaction tensor factorization for personalized tag recommendation}, url = {http://doi.acm.org/10.1145/1718487.1718498}, year = 2010 } @incollection{gemmell2010resource, abstract = {Collaborative tagging applications enable users to annotate online resources with user-generated keywords. The collection of these annotations and the way they connect users and resources produce a rich information space for users to explore. However the size, complexity and chaotic structure of these systems hamper users as they search for information. Recommenders can assist the user by suggesting resources, tags or even other users. Previous work has demonstrated that an integrative approach which exploits all three dimensions of the data (users, resources, tags) produce superior results in tag recommendation. We extend this integrative philosophy to resource recommendation. Specifically, we propose an approach for designing weighted linear hybrid resource recommenders. Through extensive experimentation on two large real world datasets, we show that the hybrid recommenders surpass the effectiveness of their constituent components while inheriting their simplicity, computational efficiency and explanatory capacity. We further introduce the notion of information channels which describe the interaction of the three dimensions. Information channels can be used to explain the effectiveness of individual recommenders or explain the relative contribution of components in the hybrid recommender.}, address = {Berlin/Heidelberg}, affiliation = {Center for Web Intelligence, School of Computing, DePaul University, Chicago, Illinois USA}, author = {Gemmell, Jonathan and Schimoler, Thomas and Mobasher, Bamshad and Burke, Robin}, booktitle = {E-Commerce and Web Technologies}, doi = {10.1007/978-3-642-15208-5_1}, editor = {Buccafurri, Francesco and Semeraro, Giovanni}, interhash = {357183305397b19624ec246b915df6ac}, intrahash = {684579385b3a4f90f5b41ce7c92ddb2a}, isbn = {978-3-642-15208-5}, keyword = {Computer Science}, pages = {1--12}, publisher = {Springer}, series = {Lecture Notes in Business Information Processing}, title = {Resource Recommendation in Collaborative Tagging Applications}, url = {http://dx.doi.org/10.1007/978-3-642-15208-5_1}, volume = 61, year = 2010 } @inproceedings{navarrobullock2011tagging, abstract = {Learning-to-rank methods automatically generate ranking functions which can be used for ordering unknown resources according to their relevance for a specific search query. The training data to construct such a model consists of features describing a document-query-pair as well as relevance scores indicating how important the document is for the query. In general, these relevance scores are derived by asking experts to manually assess search results or by exploiting user search behaviour such as click data. The human evaluation of ranking results gives explicit relevance scores, but it is expensive to obtain. Clickdata can be logged from the user interaction with a search engine, but the feedback is noisy. In this paper, we want to explore a novel source of implicit feedback for web search: tagging data. Creating relevance feedback from tagging data leads to a further source of implicit relevance feedback which helps improve the reliability of automatically generated relevance scores and therefore the quality of learning-to-rank models.}, address = {New York, NY, USA}, author = {Navarro Bullock, Beate and Jäschke, Robert and Hotho, Andreas}, booktitle = {Proceedings of the ACM WebSci Conference}, interhash = {7afaa67dfeb07f7e0b85abf2be61aff1}, intrahash = {e5a4b67ed6173e9645aab321019efd74}, location = {Koblenz, Germany}, month = jun, organization = {ACM}, pages = {1--4}, title = {Tagging data as implicit feedback for learning-to-rank}, url = {http://journal.webscience.org/463/}, vgwort = {14,8}, year = 2011 } @inproceedings{parra2009evaluation, abstract = {Motivated by the potential use of collaborative tagging systems to develop new recommender systems, we have implemented and compared three variants of user-based collaborative filtering algorithms to provide recommendations of articles on CiteULike. On our first approach, Classic Collaborative filtering (CCF), we use Pearson correlation to calculate similarity between users and a classic adjusted ratings formula to rank the recommendations. Our second approach, Neighbor-weighted Collaborative Filtering (NwCF), incorporates the amount of raters in the ranking formula of the recommendations. A modified version of the Okapi BM25 IR model over users ’ tags is implemented on our third approach to form the user neighborhood. Our results suggest that incorporating the number of raters into the algorithms leads to an improvement of precision, and they also support that tags can be considered as an alternative to Pearson correlation to calculate the similarity between users and their neighbors in a collaborative tagging system. }, author = {Parra, Denis and Brusilovsky, Peter}, booktitle = {Proceedings of the Workshop on Web 3.0: Merging Semantic Web and Social Web}, interhash = {03a51e24ecab3ad66fcc381980144fea}, intrahash = {42773258c36ccf2f59749991518d1784}, issn = {1613-0073}, location = {Torino, Italy}, month = jun, series = {CEUR Workshop Proceedings}, title = {Evaluation of Collaborative Filtering Algorithms for Recommending Articles on CiteULike}, url = {http://ceur-ws.org/Vol-467/paper5.pdf}, volume = 467, year = 2009 } @inproceedings{lee2010using, abstract = {This paper aims to combine information about users' self-defined social connections with traditional collaborative filtering (CF) to improve recommendation quality. Specifically, in the following, the users' social connections in consideration were groups. Unlike other studies which utilized groups inferred by data mining technologies, we used the information about the groups in which each user explicitly participated. The group activities are centered on common interests. People join a group to share and acquire information about a topic as a form of community of interest or practice. The information of this group activity may be a good source of information for the members. We tested whether adding the information from the users' own groups or group members to the traditional CF-based recommendations can improve the recommendation quality or not. The information about groups was combined with CF using a mixed hybridization strategy. We evaluated our approach in two ways, using the Citeulike data set and a real user study.}, acmid = {1864752}, address = {New York, NY, USA}, author = {Lee, Danielle H. and Brusilovsky, Peter}, booktitle = {Proceedings of the fourth ACM conference on Recommender systems}, doi = {10.1145/1864708.1864752}, interhash = {6fd1cbcfd94da174c910d9144467372a}, intrahash = {ec592568ca4a9f6b2ebaf41816af1ebc}, isbn = {978-1-60558-906-0}, location = {Barcelona, Spain}, numpages = {4}, pages = {221--224}, publisher = {ACM}, title = {Using self-defined group activities for improving recommendations in collaborative tagging systems}, url = {http://doi.acm.org/10.1145/1864708.1864752}, year = 2010 } @inproceedings{pera2011personalized, abstract = {Researchers, as well as ordinary users who seek information in diverse academic fields, turn to the web to search for publications of interest. Even though scholarly publication recommenders have been developed to facilitate the task of discovering literature pertinent to their users, they (i) are not personalized enough to meet users' expectations, since they provide the same suggestions to users sharing similar profiles/preferences, (ii) generate recommendations pertaining to each user's general interests as opposed to the specific need of the user, and (iii) fail to take full advantages of valuable user-generated data at social websites that can enhance their performance. To address these problems, we propose PubRec, a recommender that suggests closely-related references to a particular publication P tailored to a specific user U, which minimizes the time and efforts imposed on U in browsing through general recommended publications. Empirical studies conducted using data extracted from CiteULike (i) verify the efficiency of the recommendation and ranking strategies adopted by PubRec and (ii) show that PubRec significantly outperforms other baseline recommenders.}, acmid = {2063908}, address = {New York, NY, USA}, author = {Pera, Maria Soledad and Ng, Yiu-Kai}, booktitle = {Proceedings of the 20th ACM international conference on Information and knowledge management}, doi = {10.1145/2063576.2063908}, interhash = {c3878647328db1e4b665dbf65547ba92}, intrahash = {d335b38783be877ea4e000e0c332cef4}, isbn = {978-1-4503-0717-8}, location = {Glasgow, Scotland, UK}, numpages = {4}, pages = {2133--2136}, publisher = {ACM}, title = {A personalized recommendation system on scholarly publications}, url = {http://doi.acm.org/10.1145/2063576.2063908}, year = 2011 } @incollection{cantador2011semantic, abstract = {We present an approach that efficiently identifies the semantic meanings and contexts of social tags within a particular folksonomy, and exploits them to build contextualised tag-based user and item profiles. We apply our approach to a dataset obtained from Delicious social bookmarking system, and evaluate it through two experiments: a user study consisting of manual judgements of tag disambiguation and contextualisation cases, and an offline study measuring the performance of several tag-powered item recommendation algorithms by using contextualised profiles. The results obtained show that our approach is able to accurately determine the actual semantic meanings and contexts of tag annotations, and allow item recommenders to achieve better precision and recall on their predictions.}, address = {Berlin/Heidelberg}, affiliation = {Departamento de Ingeniería Informática, Universidad Autónoma de Madrid, 28049 Madrid, Spain}, author = {Cantador, Iván and Bellogín, Alejandro and Fernández-Tobías, Ignacio and López-Hernández, Sergio}, booktitle = {E-Commerce and Web Technologies}, doi = {10.1007/978-3-642-23014-1_9}, editor = {Huemer, Christian and Setzer, Thomas and Aalst, Wil and Mylopoulos, John and Rosemann, Michael and Shaw, Michael J. and Szyperski, Clemens}, interhash = {b2359e659cf8c02ba8e9fc8db014aafc}, intrahash = {ac6d55bacc85f75a4711a1c48526dfd6}, isbn = {978-3-642-23014-1}, keyword = {Computer Science}, pages = {101--113}, publisher = {Springer}, series = {Lecture Notes in Business Information Processing}, title = {Semantic Contextualisation of Social Tag-Based Profiles and Item Recommendations}, url = {http://dx.doi.org/10.1007/978-3-642-23014-1_9}, volume = 85, year = 2011 } @incollection{wartena2011improving, abstract = {Collaborative tagging has emerged as a mechanism to describe items in large on-line collections. Tags are assigned by users to describe and find back items, but it is also tempting to describe the users in terms of the tags they assign or in terms of the tags of the items they are interested in. The tag-based profile thus obtained can be used to recommend new items. If we recommend new items by computing their similarity to the user profile or to all items seen by the user, we run into the risk of recommending only neutral items that are a bit relevant for each topic a user is interested in. In order to increase user satisfaction many recommender systems not only optimize for accuracy but also for diversity. Often it is assumed that there exists a trade-off between accuracy and diversity. In this paper we introduce topic aware recommendation algorithms. Topic aware algorithms first detect different interests in the user profile and then generate recommendations for each of these interests. We study topic aware variants of three tag based recommendation algorithms and show that each of them gives better recommendations than their base variants, both in terms of precision and recall and in terms of diversity.}, address = {Berlin/Heidelberg}, affiliation = {Novay, Brouwerijstraat 1, 7523 XC Enschede, The Netherlands}, author = {Wartena, Christian and Wibbels, Martin}, booktitle = {Advances in Information Retrieval}, doi = {10.1007/978-3-642-20161-5_7}, editor = {Clough, Paul and Foley, Colum and Gurrin, Cathal and Jones, Gareth and Kraaij, Wessel and Lee, Hyowon and Mudoch, Vanessa}, interhash = {9bdec52c6a5e56fb68b0553440b217df}, intrahash = {fd9284874d7896d3aee8a9641efe368a}, isbn = {978-3-642-20160-8}, keyword = {Computer Science}, pages = {43--54}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Improving Tag-Based Recommendation by Topic Diversification}, url = {http://dx.doi.org/10.1007/978-3-642-20161-5_7}, volume = 6611, year = 2011 } @book{balbymarinho2012recommender, abstract = {Social Tagging Systems are web applications in which users upload resources (e.g., bookmarks, videos, photos, etc.) and annotate it with a list of freely chosen keywords called tags. This is a grassroots approach to organize a site and help users to find the resources they are interested in. Social tagging systems are open and inherently social; features that have been proven to encourage participation. However, with the large popularity of these systems and the increasing amount of user-contributed content, information overload rapidly becomes an issue. Recommender Systems are well known applications for increasing the level of relevant content over the “noise” that continuously grows as more and more content becomes available online. In social tagging systems, however, we face new challenges. While in classic recommender systems the mode of recommendation is basically the resource, in social tagging systems there are three possible modes of recommendation: users, resources, or tags. Therefore suitable methods that properly exploit the different dimensions of social tagging systems data are needed. In this book, we survey the most recent and state-of-the-art work about a whole new generation of recommender systems built to serve social tagging systems. The book is divided into self-contained chapters covering the background material on social tagging systems and recommender systems to the more advanced techniques like the ones based on tensor factorization and graph-based models.}, author = {Balby Marinho, L. and Hotho, A. and Jäschke, R. and Nanopoulos, A. and Rendle, S. and Schmidt-Thieme, L. and Stumme, G. and Symeonidis, P.}, doi = {10.1007/978-1-4614-1894-8}, interhash = {0bb7f0588cd690d67cc73e219a3a24fa}, intrahash = {87d6883ebd98e8810be45d7e7e4ade96}, isbn = {978-1-4614-1893-1}, month = feb, publisher = {Springer}, series = {SpringerBriefs in Electrical and Computer Engineering}, title = {Recommender Systems for Social Tagging Systems}, url = {http://link.springer.com/book/10.1007/978-1-4614-1894-8}, year = 2012 } @incollection{jaeschke2012challenges, abstract = {Originally introduced by social bookmarking systems, collaborative tagging, or social tagging, has been widely adopted by many web-based systems like wikis, e-commerce platforms, or social networks. Collaborative tagging systems allow users to annotate resources using freely chosen keywords, so called tags . Those tags help users in finding/retrieving resources, discovering new resources, and navigating through the system. The process of tagging resources is laborious. Therefore, most systems support their users by tag recommender components that recommend tags in a personalized way. The Discovery Challenges 2008 and 2009 of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) tackled the problem of tag recommendations in collaborative tagging systems. Researchers were invited to test their methods in a competition on datasets from the social bookmark and publication sharing system BibSonomy. Moreover, the 2009 challenge included an online task where the recommender systems were integrated into BibSonomy and provided recommendations in real time. In this chapter we review, evaluate and summarize the submissions to the two Discovery Challenges and thus lay the groundwork for continuing research in this area.}, address = {Berlin/Heidelberg}, affiliation = {Knowledge & Data Engineering Group, University of Kassel, Wilhelmshöher Allee 73, 34121 Kassel, Germany}, author = {Jäschke, Robert and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd}, booktitle = {Recommender Systems for the Social Web}, doi = {10.1007/978-3-642-25694-3_3}, editor = {Pazos Arias, José J. and Fernández Vilas, Ana and Díaz Redondo, Rebeca P.}, interhash = {75b1a6f54ef54d0126d0616b5bf77563}, intrahash = {7d41d332cccc3e7ba8e7dadfb7996337}, isbn = {978-3-642-25694-3}, pages = {65--87}, publisher = {Springer}, series = {Intelligent Systems Reference Library}, title = {Challenges in Tag Recommendations for Collaborative Tagging Systems}, url = {http://dx.doi.org/10.1007/978-3-642-25694-3_3}, volume = 32, year = 2012 } @inproceedings{kim2011personalized, abstract = {This paper looks inside FolkRank, one of the well-known folksonomy-based algorithms, to present its fundamental properties and promising possibilities for improving performance in tag recommendations. Moreover, we introduce a new way to compute a differential approach in FolkRank by representing it as a linear combination of the personalized PageRank vectors. By the linear combination, we present FolkRank's probabilistic interpretation that grasps how FolkRank works on a folksonomy graph in terms of the random surfer model. We also propose new FolkRank-like methods for tag recommendations to efficiently compute tags' rankings and thus reduce expensive computational cost of FolkRank. We show that the FolkRank approaches are feasible to recommend tags in real-time scenarios as well. The experimental evaluations show that the proposed methods provide fast tag recommendations with reasonable quality, as compared to FolkRank. Additionally, we discuss the diversity of the top n tags recommended by FolkRank and its variants.}, acmid = {2043945}, address = {New York, NY, USA}, author = {Kim, Heung-Nam and El Saddik, Abdulmotaleb}, booktitle = {Proceedings of the fifth ACM conference on Recommender systems}, doi = {10.1145/2043932.2043945}, interhash = {1004b267b14d0abde0f8ac3a7ceadd38}, intrahash = {f022e60c5928e01c701d7ec539ec221b}, isbn = {978-1-4503-0683-6}, location = {Chicago, Illinois, USA}, numpages = {8}, pages = {45--52}, publisher = {ACM}, title = {Personalized PageRank vectors for tag recommendations: inside FolkRank}, url = {http://doi.acm.org/10.1145/2043932.2043945}, year = 2011 } @inproceedings{chi2008understanding, abstract = {Given the rise in popularity of social tagging systems, it seems only natural to ask how efficient is the organically evolved tagging vocabulary in describing underlying document objects? Does this distributed process really provide a way to circumnavigate the traditional "vocabulary problem" with ontology? We analyze a social tagging site, namely del.icio.us, with information theory in order to evaluate the efficiency of this social tagging site for encoding navigation paths to information sources. We show that information theory provides a natural and interesting way to understand this efficiency - or the descriptive, encoding power of tags. Our results indicate the efficiency of tags appears to be waning. We discuss the implications of our findings and provide insight into how our methods can be used to design more usable social tagging software.}, acmid = {1379110}, address = {New York, NY, USA}, author = {Chi, Ed H. and Mytkowicz, Todd}, booktitle = {Proceedings of the nineteenth ACM conference on Hypertext and hypermedia}, doi = {10.1145/1379092.1379110}, interhash = {81c80283290d396a41015d0df11822c7}, intrahash = {d44d1c9a48f5b676388ffbc90c7577ba}, isbn = {978-1-59593-985-2}, location = {Pittsburgh, PA, USA}, numpages = {8}, pages = {81--88}, publisher = {ACM}, title = {Understanding the efficiency of social tagging systems using information theory}, url = {http://doi.acm.org/10.1145/1379092.1379110}, year = 2008 } @inproceedings{konstas2009social, abstract = {Social network systems, like last.fm, play a significant role in Web 2.0, containing large amounts of multimedia-enriched data that are enhanced both by explicit user-provided annotations and implicit aggregated feedback describing the personal preferences of each user. It is also a common tendency for these systems to encourage the creation of virtual networks among their users by allowing them to establish bonds of friendship and thus provide a novel and direct medium for the exchange of data. We investigate the role of these additional relationships in developing a track recommendation system. Taking into account both the social annotation and friendships inherent in the social graph established among users, items and tags, we created a collaborative recommendation system that effectively adapts to the personal information needs of each user. We adopt the generic framework of Random Walk with Restarts in order to provide with a more natural and efficient way to represent social networks. In this work we collected a representative enough portion of the music social network last.fm, capturing explicitly expressed bonds of friendship of the user as well as social tags. We performed a series of comparison experiments between the Random Walk with Restarts model and a user-based collaborative filtering method using the Pearson Correlation similarity. The results show that the graph model system benefits from the additional information embedded in social knowledge. In addition, the graph model outperforms the standard collaborative filtering method.}, acmid = {1571977}, address = {New York, NY, USA}, author = {Konstas, Ioannis and Stathopoulos, Vassilios and Jose, Joemon M.}, booktitle = {Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval}, doi = {10.1145/1571941.1571977}, interhash = {9dde0442dfcf24151811f301fb7fa3cb}, intrahash = {3a2c3898216376eab27848a7f147ee51}, isbn = {978-1-60558-483-6}, location = {Boston, MA, USA}, numpages = {8}, pages = {195--202}, publisher = {ACM}, series = {SIGIR '09}, title = {On social networks and collaborative recommendation}, url = {http://doi.acm.org/10.1145/1571941.1571977}, year = 2009 } @article{peterson2006beneath, author = {Peterson, Elaine}, doi = {10.1045/november2006-peterson}, interhash = {11b682c7b3141988594d05dbd09fcd54}, intrahash = {9d4746291e69e3dbe5fdd1a3e38417f1}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = nov, number = 11, title = {Beneath the Metadata: Some Philosophical Problems with Folksonomy }, url = {http://www.dlib.org/dlib/november06/peterson/11peterson.html}, volume = 12, year = 2006 } @inproceedings{clements2007personalization, abstract = {This article describes a framework that captures collaborative tagging systems, and derives from it an overview of user tasks that qualify for personalization in such a system. Major research areas have focused on some of these tasks, but we identify many more opportunities. We propose a collaborative model that combines collaborative filtering and information retrieval techniques in order to assists the user to achieve these tasks. Based only on the user's tags, this personalization model assumes that a user's tags identify this user's taste. Because many users do not only tag the content that matches their taste, we propose an evaluating experiment that shows if rating information can be used to adjust the users' taste profiles. This experiment is one of the steps to advance to a completely personalized model, integrating user preference, content annotations and people relations.}, author = {Clements, M.}, booktitle = {Proceedings of BCS IRSG Symposium: Future Directions in Information Access 2007}, interhash = {4e817e20bc7caf0a8e1111e882700383}, intrahash = {fe43da7e093f06c36010358724d03b7b}, location = {Glasgow, UK}, month = aug, title = {Personalization of Social Media}, year = 2007 } @inproceedings{lipczak2010learning, abstract = {The objective of a tag recommendation system is to propose a set of tags for a resource to ease the tagging process done manually by a user. Tag recommendation is an interesting and well defined research problem. However, while solving it, it is easy to forget about its practical implications. We discuss the practical aspects of tag recommendation and propose a system that successfully addresses the problem of learning in tag recommendation, without sacrificing efficiency. Learning is realized in two aspects: adaptation to newly added posts and parameter tuning. The content of each added post is used to update the resource and user profiles as well as associations between tags. Parameter tuning allows the system to automatically adjust the way tag sources (e.g., content related tags or user profile tags) are combined to match the characteristics of a specific collaborative tagging system. The evaluation on data from three collaborative tagging systems confirmed the importance of both learning methods. Finally, an architecture based on text indexing makes the system efficient enough to serve in real time collaborative tagging systems with number of posts counted in millions, given limited computing resources.}, acmid = {1864741}, address = {New York, NY, USA}, author = {Lipczak, Marek and Milios, Evangelos}, booktitle = {Proceedings of the fourth ACM conference on Recommender systems}, doi = {10.1145/1864708.1864741}, interhash = {ead36cc0857c37506a187f08636584b8}, intrahash = {0dad64a7e8e7fbfe51a4fc22ee533a1a}, isbn = {978-1-60558-906-0}, location = {Barcelona, Spain}, numpages = {8}, pages = {167--174}, publisher = {ACM}, series = {RecSys '10}, title = {Learning in efficient tag recommendation}, url = {http://doi.acm.org/10.1145/1864708.1864741}, year = 2010 } @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{cattuto2007network, abstract = {Social resource sharing systems like YouTube and del.icio.us have acquired a large number of users within the last few years. They provide rich resources for data analysis, information retrieval, and knowledge discovery applications. A first step towards this end is to gain better insights into content and structure of these systems. In this paper, we will analyse the main network characteristics of two of these systems. We consider their underlying data structures - so-called folksonomies - as tri-partite hypergraphs, and adapt classical network measures like characteristic path length and clustering coefficient to them. Subsequently, we introduce a network of tag co-occurrence and investigate some of its statistical properties, focusing on correlations in node connectivity and pointing out features that reflect emergent semantics within the folksonomy. We show that simple statistical indicators unambiguously spot non-social behavior such as spam. }, address = {Amsterdam, The Netherlands}, 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}, interhash = {fc5f2df61d28bc99b7e15029da125588}, intrahash = {f15cc7613101babb2c3ed1927e35213a}, issn = {0921-7126}, journal = {AI Communications}, month = dec, number = 4, pages = {245--262}, publisher = {IOS Press}, title = {Network Properties of Folksonomies}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/cattuto2007network.pdf}, volume = 20, year = 2007 } @article{jaeschke2008discovering, abstract = {Social bookmarking tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. Unlike ontologies, shared conceptualizations are not formalized, but rather implicit. We present a new data mining task, the mining of all frequent tri-concepts, together with an efficient algorithm, for discovering these implicit shared conceptualizations. Our approach extends the data mining task of discovering all closed itemsets to three-dimensional data structures to allow for mining folksonomies. We provide a formal definition of the problem, and present an efficient algorithm for its solution. Finally, we show the applicability of our approach on three large real-world examples.}, address = {New York}, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd}, booktitle = {Semantic Web and Web 2.0}, doi = {10.1016/j.websem.2007.11.004}, editor = {Finin, T. and Mizoguchi, R. and Staab, S.}, interhash = {cfca594f9dbe30694bfbcdeb40dc4e88}, intrahash = {18e8babe208fae2c0342438617b0ec31}, issn = {1570-8268}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, month = feb, number = 1, pages = {38--53}, publisher = {Elsevier}, title = {Discovering Shared Conceptualizations in Folksonomies}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/jaeschke2008discovering.pdf}, vgwort = {59}, volume = 6, year = 2008 }