@phdthesis{NavarroBullock2015,
  author    = {Navarro Bullock, Beate},
  title     = {Privacy aware social information retrieval and spam filtering using folksonomies},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-120941},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2015},
  abstract  = {Social interactions as introduced by Web 2.0 applications during the last decade have changed the way the Internet is used. Today, it is part of our daily lives to maintain contacts through social networks, to comment on the latest developments in microblogging services or to save and share information snippets such as photos or bookmarks online. Social bookmarking systems are part of this development. Users can share links to interesting web pages by publishing bookmarks and providing descriptive keywords for them. The structure which evolves from the collection of annotated bookmarks is called a folksonomy. The sharing of interesting and relevant posts enables new ways of retrieving information from the Web. Users can search or browse the folksonomy looking at resources related to specific tags or users. Ranking methods known from search engines have been adjusted to facilitate retrieval in social bookmarking systems. Hence, social bookmarking systems have become an alternative or addendum to search engines. In order to better understand the commonalities and differences of social bookmarking systems and search engines, this thesis compares several aspects of the two systems' structure, usage behaviour and content. This includes the use of tags and query terms, the composition of the document collections and the rankings of bookmarks and search engine URLs. Searchers (recorded via session ids), their search terms and the clicked on URLs can be extracted from a search engine query logfile. They form similar links as can be found in folksonomies where a user annotates a resource with tags. We use this analogy to build a tripartite hypergraph from query logfiles (a logsonomy), and compare structural and semantic properties of log- and folksonomies. Overall, we have found similar behavioural, structural and semantic characteristics in both systems. Driven by this insight, we investigate, if folksonomy data can be of use in web information retrieval in a similar way to query log data: we construct training data from query logs and a folksonomy to build models for a learning-to-rank algorithm. First experiments show a positive correlation of ranking results generated from the ranking models of both systems. The research is based on various data collections from the social bookmarking systems BibSonomy and Delicious, Microsoft's search engine MSN (now Bing) and Google data. To maintain social bookmarking systems as a good source for information retrieval, providers need to fight spam. This thesis introduces and analyses different features derived from the specific characteristics of social bookmarking systems to be used in spam detection classification algorithms. Best results can be derived from a combination of profile, activity, semantic and location-based features. Based on the experiments, a spam detection framework which identifies and eliminates spam activities for the social bookmarking system BibSonomy has been developed. The storing and publication of user-related bookmarks and profile information raises questions about user data privacy. What kinds of personal information is collected and how do systems handle user-related items? In order to answer these questions, the thesis looks into the handling of data privacy in the social bookmarking system BibSonomy. Legal guidelines about how to deal with the private data collected and processed in social bookmarking systems are also presented. Experiments will show that the consideration of user data privacy in the process of feature design can be a first step towards strengthening data privacy.},
  subject      = {Information Retrieval},
  language  = {en}
}
@phdthesis{Winkler2015,
  author    = {Winkler, Marco},
  title     = {On the Role of Triadic Substructures in Complex Networks},
  publisher = {epubli GmbH},
  address   = {Berlin},
  isbn      = {978-3-7375-5654-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-116022},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2015},
  abstract  = {In the course of the growth of the Internet and due to increasing availability of data, over the last two decades, the field of network science has established itself as an own area of research. With quantitative scientists from computer science, mathematics, and physics working on datasets from biology, economics, sociology, political sciences, and many others, network science serves as a paradigm for interdisciplinary research. One of the major goals in network science is to unravel the relationship between topological graph structure and a network's function. As evidence suggests, systems from the same fields, i.e. with similar function, tend to exhibit similar structure. However, it is still vague whether a similar graph structure automatically implies likewise function. This dissertation aims at helping to bridge this gap, while particularly focusing on the role of triadic structures. After a general introduction to the main concepts of network science, existing work devoted to the relevance of triadic substructures is reviewed. A major challenge in modeling triadic structure is the fact that not all three-node subgraphs can be specified independently of each other, as pairs of nodes may participate in multiple of those triadic subgraphs. In order to overcome this obstacle, we suggest a novel class of generative network models based on so called Steiner triple systems. The latter are partitions of a graph's vertices into pair-disjoint triples (Steiner triples). Thus, the configurations on Steiner triples can be specified independently of each other without overdetermining the network's link structure. Subsequently, we investigate the most basic realization of this new class of models. We call it the triadic random graph model (TRGM). The TRGM is parametrized by a probability distribution over all possible triadic subgraph patterns. In order to generate a network instantiation of the model, for all Steiner triples in the system, a pattern is drawn from the distribution and adjusted randomly on the Steiner triple. We calculate the degree distribution of the TRGM analytically and find it to be similar to a Poissonian distribution. Furthermore, it is shown that TRGMs possess non-trivial triadic structure. We discover inevitable correlations in the abundance of certain triadic subgraph patterns which should be taken into account when attributing functional relevance to particular motifs - patterns which occur significantly more frequently than expected at random. Beyond, the strong impact of the probability distributions on the Steiner triples on the occurrence of triadic subgraphs over the whole network is demonstrated. This interdependence allows us to design ensembles of networks with predefined triadic substructure. Hence, TRGMs help to overcome the lack of generative models needed for assessing the relevance of triadic structure. We further investigate whether motifs occur homogeneously or heterogeneously distributed over a graph. Therefore, we study triadic subgraph structures in each node's neighborhood individually. In order to quantitatively measure structure from an individual node's perspective, we introduce an algorithm for node-specific pattern mining for both directed unsigned, and undirected signed networks. Analyzing real-world datasets, we find that there are networks in which motifs are distributed highly heterogeneously, bound to the proximity of only very few nodes. Moreover, we observe indication for the potential sensitivity of biological systems to a targeted removal of these critical vertices. In addition, we study whole graphs with respect to the homogeneity and homophily of their node-specific triadic structure. The former describes the similarity of subgraph distributions in the neighborhoods of individual vertices. The latter quantifies whether connected vertices are structurally more similar than non-connected ones. We discover these features to be characteristic for the networks' origins. Moreover, clustering the vertices of graphs regarding their triadic structure, we investigate structural groups in the neural network of C. elegans, the international airport-connection network, and the global network of diplomatic sentiments between countries. For the latter we find evidence for the instability of triangles considered socially unbalanced according to sociological theories. Finally, we utilize our TRGM to explore ensembles of networks with similar triadic substructure in terms of the evolution of dynamical processes acting on their nodes. Focusing on oscillators, coupled along the graphs' edges, we observe that certain triad motifs impose a clear signature on the systems' dynamics, even when embedded in a larger network structure.},
  subject      = {Netzwerk},
  language  = {en}
}