Refine
Year of publication
Document Type
- Master's Thesis (17)
- Part of Periodical (14)
- Doctoral Thesis (11)
- Bachelor Thesis (3)
- Study Thesis (2)
- Diploma Thesis (1)
- Habilitation (1)
Language
- English (49) (remove)
Keywords
- ontology (3)
- Linked Open Data (2)
- Maschinelles Lernen (2)
- mobile phone (2)
- multimedia metadata (2)
- 2019 European Parliament Election (1)
- API (1)
- Algolib (1)
- Analysis of social platform (1)
- Annotation (1)
Institute
- Institute for Web Science and Technologies (49) (remove)
In this thesis, I study the spectral characteristics of large dynamic networks and formulate the spectral evolution model. The spectral evolution model applies to networks that evolve over time, and describes their spectral decompositions such as the eigenvalue and singular value decomposition. The spectral evolution model states that over time, the eigenvalues of a network change while its eigenvectors stay approximately constant.
I validate the spectral evolution model empirically on over a hundred network datasets, and theoretically by showing that it generalizes arncertain number of known link prediction functions, including graph kernels, path counting methods, rank reduction and triangle closing. The collection of datasets I use contains 118 distinct network datasets. One dataset, the signed social network of the Slashdot Zoo, was specifically extracted during work on this thesis. I also show that the spectral evolution model can be understood as a generalization of the preferential attachment model, if we consider growth in latent dimensions of a network individually. As applications of the spectral evolution model, I introduce two new link prediction algorithms that can be used for recommender systems, search engines, collaborative filtering, rating prediction, link sign prediction and more.
The first link prediction algorithm reduces to a one-dimensional curve fitting problem from which a spectral transformation is learned. The second method uses extrapolation of eigenvalues to predict future eigenvalues. As special cases, I show that the spectral evolution model applies to directed, undirected, weighted, unweighted, signed and bipartite networks. For signed graphs, I introduce new applications of the Laplacian matrix for graph drawing, spectral clustering, and describe new Laplacian graph kernels. I also define the algebraic conflict, a measure of the conflict present in a signed graph based on the signed graph Laplacian. I describe the problem of link sign prediction spectrally, and introduce the signed resistance distance. For bipartite and directed graphs, I introduce the hyperbolic sine and odd Neumann kernels, which generalize the exponential and Neumann kernels for undirected unipartite graphs. I show that the problem of directed and bipartite link prediction are related by the fact that both can be solved by considering spectral evolution in the singular value decomposition.
We present the user-centered, iterative design of Mobile Facets, a mobile application for the faceted search and exploration of a large, multi-dimensional data set of social media on a touchscreen mobile phone. Mobile Facets provides retrieval of resources such as places, persons, organizations, and events from an integration of different open social media sources and professional content sources, namely Wikipedia, Eventful, Upcoming, geo-located Flickr photos, and GeoNames. The data is queried live from the data sources. Thus, in contrast to other approaches we do not know in advance the number and type of facets and data items the Mobile Facets application receives in a specific contextual situation. While developingrnMobile Facets, we have continuously evaluated it with a small group of fifive users. We have conducted a task-based, formative evaluation of the fifinal prototype with 12 subjects to show the applicability and usability of our approach for faceted search and exploration on a touchscreen mobile phone.
The Multimedia Metadata Ontology (M3O) provides a generic modeling framework for representing multimedia metadata. It has been designed based on an analysis of existing metadata standards and metadata formats. The M3O abstracts from the existing metadata standards and formats and provides generic modeling solutions for annotations, decompositions, and provenance of metadata. Being a generic modeling framework, the M3O aims at integrating the existing metadata standards and metadata formats rather than replacing them. This is in particular useful as today's multimedia applications often need to combine and use more than one existing metadata standard or metadata format at the same time. However, applying and specializing the abstract and powerful M3O modeling framework in concrete application domains and integrating it with existing metadata formats and metadata standards is not always straightforward. Thus, we have developed a step-by-step alignment method that describes how to integrate existing multimedia metadata standards and metadata formats with the M3O in order to use them in a concrete application. We demonstrate our alignment method by integrating seven different existing metadata standards and metadata formats with the M3O and describe the experiences made during the integration process.
In this paper, we compare two approaches for exploring large,rnhierarchical data spaces of social media data on mobile devicesrnusing facets. While the first approach arranges thernfacets in a 3x3 grid, the second approach makes use of arnscrollable list of facets for exploring the data. We have conductedrna between-group experiment of the two approachesrnwith 24 subjects (20 male, 4 female) executing the same set ofrntasks of typical mobile users" information needs. The resultsrnshow that the grid-based approach requires significantly morernclicks, but subjects need less time for completing the tasks.rnFurthermore, it shows that the additional clicks do not hamperrnthe subjects" satisfaction. Thus, the results suggest thatrnthe grid-based approach is a better choice for faceted searchrnon touchscreen mobile devices. To the best of our knowledge,rnsuch a summative evaluation of different approaches for facetedrnsearch on mobile devices has not been done so far.
Schema information about resources in the Linked Open Data (LOD) cloud can be provided in a twofold way: it can be explicitly defined by attaching RDF types to the resources. Or it is provided implicitly via the definition of the resources´ properties.
In this paper, we analyze the correlation between the two sources of schema information. To this end, we have extracted schema information regarding the types and properties defined in two datasets of different size. One dataset is a LOD crawl from TimBL- FOAF profile (11 Mio. triple) and the second is an extract from the Billion Triples Challenge 2011 dataset (500 Mio. triple). We have conducted an in depth analysis and have computed various entropy measures as well as the mutual information encoded in this two manifestations of schema information.
Our analysis provides insights into the information encoded in the different schema characteristics. It shows that a schema based on either types or properties alone will capture only about 75% of the information contained in the data. From these observations, we derive conclusions about the design of future schemas for LOD.
Various best practices and principles guide an ontology engineer when modeling Linked Data. The choice of appropriate vocabularies is one essential aspect in the guidelines, as it leads to better interpretation, querying, and consumption of the data by Linked Data applications and users.
In this paper, we present the various types of support features for an ontology engineer to model a Linked Data dataset, discuss existing tools and services with respect to these support features, and propose LOVER: a novel approach to support the ontology engineer in modeling a Linked Data dataset. We demonstrate that none of the existing tools and services incorporate all types of supporting features and illustrate the concept of LOVER, which supports the engineer by recommending appropriate classes and properties from existing and actively used vocabularies. Hereby, the recommendations are made on the basis of an iterative multimodal search. LOVER uses different, orthogonal information sources for finding terms, e.g. based on a best string match or schema information on other datasets published in the Linked Open Data cloud. We describe LOVER's recommendation mechanism in general and illustrate it alongrna real-life example from the social sciences domain.
Tagging systems are intriguing dynamic systems, in which users collaboratively index resources with the so-called tags. In order to leverage the full potential of tagging systems, it is important to understand the relationship between the micro-level behavior of the individual users and the macro-level properties of the whole tagging system. In this thesis, we present the Epistemic Dynamic Model, which tries to bridge this gap between the micro-level behavior and the macro-level properties by developing a theory of tagging systems. The model is based on the assumption that the combined influence of the shared background knowledge of the users and the imitation of tag recommendations are sufficient for explaining the emergence of the tag frequency distribution and the vocabulary growth in tagging systems. Both macro-level properties of tagging systems are closely related to the emergence of the shared community vocabulary. rnrnWith the help of the Epistemic Dynamic Model, we show that the general shape of the tag frequency distribution and of the vocabulary growth have their origin in the shared background knowledge of the users. Tag recommendations can then be used for selectively influencing this general shape. In this thesis, we especially concentrate on studying the influence of recommending a set of popular tags. Recommending popular tags adds a feedback mechanism between the vocabularies of individual users that increases the inter-indexer consistency of the tag assignments. How does this influence the indexing quality in a tagging system? For this purpose, we investigate a methodology for measuring the inter-resource consistency of tag assignments. The inter-resource consistency is an indicator of the indexing quality, which positively correlates with the precision and recall of query results. It measures the degree to which the tag vectors of indexed resources reflect how the users perceive the similarity between resources. We argue with our model, and show it with a user experiment, that recommending popular tags decreases the inter-resource consistency in a tagging system. Furthermore, we show that recommending the user his/her previously used tags helps to increase the inter-resource consistency. Our measure of the inter-resource consistency complements existing measures for the evaluation and comparison of tag recommendation algorithms, moving the focus to evaluating their influence on the indexing quality.
The way information is presented to users in online community platforms has an influence on the way the users create new information. This is the case, for instance, in question-answering fora, crowdsourcing platforms or other social computation settings. To better understand the effects of presentation policies on user activity, we introduce a generative model of user behaviour in this paper. Running simulations based on this user behaviour we demonstrate the ability of the model to evoke macro phenomena comparable to the ones observed on real world data.
Modeling and publishing Linked Open Data (LOD) involves the choice of which vocabulary to use. This choice is far from trivial and poses a challenge to a Linked Data engineer. It covers the search for appropriate vocabulary terms, making decisions regarding the number of vocabularies to consider in the design process, as well as the way of selecting and combining vocabularies. Until today, there is no study that investigates the different strategies of reusing vocabularies for LOD modeling and publishing. In this paper, we present the results of a survey with 79 participants that examines the most preferred vocabulary reuse strategies of LOD modeling. Participants of our survey are LOD publishers and practitioners. Their task was to assess different vocabulary reuse strategies and explain their ranking decision. We found significant differences between the modeling strategies that range from reusing popular vocabularies, minimizing the number of vocabularies, and staying within one domain vocabulary. A very interesting insight is that the popularity in the meaning of how frequent a vocabulary is used in a data source is more important than how often individual classes and properties arernused in the LOD cloud. Overall, the results of this survey help in understanding the strategies how data engineers reuse vocabularies, and theyrnmay also be used to develop future vocabulary engineering tools.
Next word prediction is the task of suggesting the most probable word a user will type next. Current approaches are based on the empirical analysis of corpora (large text files) resulting in probability distributions over the different sequences that occur in the corpus. The resulting language models are then used for predicting the most likely next word. State-of-the-art language models are based on n-grams and use smoothing algorithms like modified Kneser-Ney smoothing in order to reduce the data sparsity by adjusting the probability distribution of unseen sequences. Previous research has shown that building word pairs with different distances by inserting wildcard words into the sequences can result in better predictions by further reducing data sparsity. The aim of this thesis is to formalize this novel approach and implement it by also including modified Kneser-Ney smoothing.