BibSonomy publications for /user/dbenz/diploma_thesisFri Mar 07 17:57:51 CET 2008D-LibJanuary1Folksonomies: Tidying Up Tags?122006tagging improve_tags delicious folksonomy_background folksonomy diploma_thesis flickr A folksonomy is a type of distributed classification system. It is usually created by a group of individuals, typically the resource users. Users add tags to online items, such as images, videos, bookmarks and text. These tags are then shared and sometimes refined. In this article we look at what makes folksonomies work. We agree with the premise that tags are no replacement for formal systems, but we see this as being the core quality that makes folksonomy tagging so useful.Mon Dec 10 09:30:22 CET 2007Workshop Proceedings of Lernen - Wissensentdeckung - Adaptivität (LWA 2007)sep109--112Position Paper: Ontology Learning from Folksonomies2007ontology_learning myown diploma_thesis tagorapub 2007 Thu Oct 25 07:50:32 CEST 2007GermanyDecemberMeasuring the Similarity of Concept Hierarchies and its Influence on the Evaluation of Learning Procedures2005diploma_thesis evaluation_methods The information available in corporate intranets and in the Internet grows from day to day. Looking for a specific information often the question is how to find it. Therefore it is the aim of researchers to allow a more efficient access to large collections of information. Many of the developed algorithms are dependent on additional domain knowledge for improving the achieved results (see (Gonzalo et al., 1998) and (De Buenaga Rodr�guez et al., 2000)). The domain knowledge is often available in the form of ontologies. An ontology reflects the understanding of a domain, on which a community has agreed upon. An ontology consists of different parts like a set of concepts and their mutual relations. These concepts are organized in a hierarchy of sub- and superconcepts. In order to actually improve the results of an application with the help of an ontology, it is crucial to accurately and exhaustively model the domain in question. Because this is a very complex and time consuming task it is a goal to extract an ontology at least semi-automatically. Such learning procedures use documents from the domain for extracting the necessary information. Often these documents are natural language texts like websites or dictionaries which contain domain knowledge (see (Kietz, Maedche and Volz, 2000) and (Cimiano, Hotho and Staab, 2004)). The quality of an automatically learned ontology is basically influenced by two parameters: The actual learning procedure and the document corpus. There exist several alternative learning procedures. They are further differentiated by the types of documents which they can process, i.e. whether they can process unstructured, semi-structured or structured documents. Websites are an example for unstructured documents, while dictionary entries and encyclopedia articles are examples for semi-structured documents. Documents containing artificial languages like database schemes are finally classified as structured documents. It is often assumed that the availability of structural information leads to a better quality of the extracted ontology. In order to enable a comparison of the different learning procedures, so that one can choose the best procedure for a certain purpose, they are often evaluated on an example corpus of documents. Subsequently it is tried to objectively measure the quality of the extracted ontology. Such an evaluation may also be used for fine tuning the parameters of a learning procedure, so that better results are achieved. One way of objectively evaluating a learning procedure is to measure the similarity between the learned ontology and a previously defined reference ontology. This similarity is then an equivalent for the quality. It is assumed that the learning procedure will always produce results with a comparable quality. This quality will only be influenced by the document corpus which must contain the correct informations.Tue Sep 11 13:31:43 CEST 2007Proceedings of the WWW2006submittedComputing Semantic Proximity Between Concepts Using Taxonomic Knowledge2006diploma_thesis eventually_useful Tue Sep 11 13:31:43 CEST 2007Chiba, JapanProceedings of the 14th International World Wide Web ConferenceMayImproving Recommendation Lists Through Topic Diversification2005diploma_thesis eventually_useful In this work we present topic diversification, a novel method designed to balance and diversify personalized recommenda- tion lists in order to reflect the user�s complete spectrum of interests. Though being detrimental to average accuracy, we show that our method improves user satisfaction with rec- ommendation lists, in particular for lists generated using the common item-based collaborative filtering algorithm. Our work builds upon prior research on recommender sys- tems, looking at properties of recommendation lists as en- tities in their own right rather than specifically focusing on the accuracy of individual recommendations. We introduce the intra-list similarity metric to assess the topical diver- sity of recommendation lists and the topic diversification approach for decreasing the intra-list similarity. We evalu- ate our method using book recommendation data, including online analysis on 361, 349 ratings and an online study in- volving more than 2, 100 subjects.Tue Sep 11 13:31:42 CEST 2007Journal on Data Semantics VIEmergent Semantics from Folksonomies: A Quantitative Study2006closely_related diploma_thesis Defining and using ontology to annotate web resources with semantic markups is generally perceived as the primary way to implement the vision of the Semantic Web. The ontology provides a shared and machine understandable semantics for web resources that agents and applications can utilize. This top-down approach (in the sense that an ontology is defined first on top of existing web resources and then used later to markup them), however, has a high barrier to entry and is difficult to scale up. In this paper, we investigate using a bottom-up approach for semantically annotating web resources as supported by the now widely popular social bookmarks services on the web where users can annotate and categorize web resources using �tags� freely choosen by the user without any pre-existing global semantic model. This kind of informal social categories is coined as �folksonomies�. We show how global semantics can be statistically inferred from the folksonomies to semantically annotate the web resources. The global semantic model also disambiguate the tags and group synonymous tags together. Finally, we show that there indeed are hierarchical relations among the emerged concepts in the folksonomy and it is plausible to further identify them if we use more advanced probabilistic models.Tue Sep 11 13:31:42 CEST 2007Berlin / HeidelbergAdvances in Applied Artificial IntelligenceAugust982--989Lecture Notes in Computer ScienceTowards Automatic Concept Hierarchy Generation for Specific Knowledge Network.40312006eventually_useful concept_hierarchy diploma_thesis cluster_partitioning tree_similarity. hierarchical_clustering This paper discusses the automatic concept hierarchy generation process for specific knowledge network. Traditional concept hierarchy generation uses hierarchical clustering to group similar terms, and the result hierarchy is usually not satisfactory for human being recognition. Human-provided knowledge network presents strong semantic features, but this generation process is both labor-intensive and inconsistent under large scale hierarchy. The method proposed in this paper combines the results of specific knowledge network and automatic concept hierarchy generation, which produces a human-readable, semantic-oriented hierarchy. This generation process can efficiently reduce manual classification efforts, which is an exhausting task for human beings. An evaluation method is also proposed in this paper to verify the quality of the result hierarchy.Tue Sep 11 13:31:41 CEST 2007Edinburgh, ScotlandProceedings of the Collaborative Web Tagging Workshop at the WWW 2006MayTowards the Semantic Web: Collaborative Tag Suggestions2006folksonomy closely_related tagging diploma_thesis Content organization over the Internet went through several interesting phases of evolution: from structured directories to unstructured Web search engines and more recently, to tagging as a way for aggregating information, a step towards the semantic web vision. Tagging allows ranking and data organization to directly utilize inputs from end users, enabling machine processing of Web content. Since tags are created by individual users in a free form, one important problem facing tagging is to identify most appropriate tags, while eliminating noise and spam. For this purpose, we define a set of general criteria for a good tagging system. These criteria include high coverage of multiple facets to ensure good recall, least effort to reduce the cost involved in browsing, and high popularity to ensure tag quality. We propose a collaborative tag suggestion algorithm using these criteria to spot high-quality tags. The proposed algorithm employs a goodness measure for tags derived from collective user authorities to combat spam. The goodness measure is iteratively adjusted by a reward-penalty algorithm, which also incorporates other sources of tags, e.g., content-based auto-generated tags. Our experiments based on My Web 2.0 show that the algorithm is effective.Tue Sep 11 13:31:41 CEST 2007New York, NY, USAWWW '06: Proceedings of the 15th international conference on World Wide Web417--426Exploring social annotations for the semantic web2006closely_related tagging semantic_web folksonomy diploma_thesis Tue Sep 11 13:31:41 CEST 2007New York, NY, USAHYPERTEXT '06: Proceedings of the seventeenth conference on Hypertext and hypermedia111--114Harvesting social knowledge from folksonomies2006diploma_thesis closely_related Collaborative tagging systems, or folksonomies, have the potential of becoming technological infrastructure to support knowledge management activities in an organization or a society. There are many challenges, however. This paper presents designs that enhance collaborative tagging systems to meet some key challenges: community identification, ontology generation, user and document recommendation. Design prototypes, evaluation methodology and selected preliminary results are presented.Tue Sep 11 13:31:40 CEST 2007netWorkerSeptember316--23The power of collective intelligence92005folksonomy_background diploma_thesis Tue Sep 11 13:31:39 CEST 2007Conceptual Modeling - ER 2006325--338Concept Modeling by the Masses: Folksonomy Structure and Interoperability2006diploma_thesis folksonomy conceptual-modeling folksonomy_background Tue Sep 11 13:31:39 CEST 2007Berlin / HeidelbergNatural Language Processing and Information SystemsJuly58-69Lecture Notes in Computer ScienceThe Language of Folksonomies: What Tags Reveal About User Classification.3999/20062006folksonomy_background diploma_thesis Folksonomies are classification schemes that emerge from the collective actions of users who tag resources with an unrestricted set of key terms. There has been a flurry of activity in this domain recently with a number of high profile web sites and search engines adopting the practice. They have sparked a great deal of excitement and debate in the popular and technical literature, accompanied by a number of analyses of the statistical properties of tagging behavior. However, none has addressed the deep nature of folksonomies. What is the nature of a tag? Where does it come from? How is it related to a resource? In this paper we present a study in which the linguistic properties of folksonomies reveal them to contain, on the one hand, tags that are similar to standard categories in taxonomies. But on the other hand, they contain additional tags to describe class properties. The implications of the findings for the relationship between folksonomy and ontology are discussed.Tue Sep 11 13:31:37 CEST 2007A cognitive analysis of tagging2005folksonomy_background diploma_thesis Tue Sep 11 13:31:36 CEST 2007MayOntology is Overrated: Categories, Links and Tags2005folksonomy_background diploma_thesis Today I want to talk about categorization, and I want to convince you that a lot of what we think we know about categorization is wrong. In particular, I want to convince you that many of the ways we're attempting to apply categorization to the electronic world are actually a bad fit, because we've adopted habits of mind that are left over from earlier strategies. I also want to convince you that what we're seeing when we see the Web is actually a radical break with previous categorization strategies, rather than an extension of them. The second part of the talk is more speculative, because it is often the case that old systems get broken before people know what's going to take their place. (Anyone watching the music industry can see this at work today.) That's what I think is happening with categorization.Tue Sep 11 13:31:36 CEST 2007SepFolksonomy as a Complex Network2005folksonomy_background diploma_thesis Folksonomy is an emerging technology that works to classify the information over WWW through tagging the bookmarks, photos or other web-based contents. It is understood to be organized by every user while not limited to the authors of the contents and the professional editors. This study surveyed the folksonomy as a complex network. The result indicates that the network, which is composed of the tags from the folksonomy, displays both properties of small world and scale-free. However, the statistics only shows a local and static slice of the vast body of folksonomy which is still evolving.Tue Sep 11 13:31:36 CEST 2007Edinburgh, ScotlandProceedings of the Workshop on Collaborative Tagging at WWW2006MayInducing Ontology from Flickr Tags2006closely_related web2.0 informationretrieval tagging linguistics flickr diploma_thesis In this paper, we describe some promising initial results in inducing ontology from the Flickr tag vocabulary, using a subsumption-based model. We describe the utility of faceted ontology as a supplement to a tagging system and present our model and results. We propose a revised, probabilistic model using seed ontologies to induce faceted ontology, and describe how the model can integrate into the logistics of tagging communities.Tue Sep 11 13:31:35 CEST 2007273-290Kollaboratives Wissensmanagement2006collaborative 2006 diploma_thesis knowledge_management folksonomy_background folksonomy Wissensmanagement Wissensmanagement in zentralisierten Wissensbasen erfordert einen hohen Aufwand f�r Erstellung und Wartung, und es entspricht nicht immer den Anforderungen der Benutzer. Wir geben in diesem Kapitel einen �berblick �ber zwei aktuelle Ans�tze, die durch kollaboratives Wissensmanagement diese Probleme l�sen k�nnen. Im Peer-to-Peer-Wissensmanagement unterhalten Benutzer dezentrale Wissensbasen, die dann vernetzt werden k�nnen, um andere Benutzer eigene Inhalte nutzen zu lassen. Folksonomies versprechen, die Wissensakquisition so einfach wie m�glich zu gestalten und so viele Benutzer in den Aufbau und die Pflege einer gemeinsamen Wissensbasis einzubeziehen.Tue Sep 11 13:31:35 CEST 2007HeidelbergData Science and Classification. Proceedings of the 10th IFCS Conf.July261--270Studies in Classification, Data Analysis, and Knowledge OrganizationMining Association Rules in Folksonomies2006network diploma_thesis closely_related semantic nepomuk folksonomy analysis 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.Tue Sep 11 13:31:34 CEST 2007Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'99206--213Deriving concept hierarchies from text1999closely_related diploma_thesis