@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}
}