Vedran Sabol

• Dr.techn.
• Research Area Manager at Know-Center

Exploring large datasets and identifying meaningful information is still an active topic in many application fields. Dealing with large datasets is currently not only a matter of simply collecting and structuring data for retrieval, but sometimes it also requires the provision of adequate means for guiding the user through the exploration process....

Whenever users engage in gathering and organizing new information, searching and browsing activities emerge at the core of the exploration process. As the process unfolds and new knowledge is acquired, interest drifts occur inevitably and need to be accounted for. Despite the advances in retrieval and recommender algorithms, real-world interfaces h...

More and more learning activities take place online in a self-directed manner. Therefore, just as the idea of self-tracking activities for fitness purposes has gained momentum in the past few years, tools and methods for awareness and self-reflection on one's own online learning behavior appear as an emerging need for both formal and informal learn...

Content based recommender systems are commonly applied to provide automatic support to users searching for relevant information. However, as the retrieved number of resources may grow large, and because the user does not have direct control over the search process, re-finding and analyzing the retrieved information can become a difficult task. We i...

When using classical search engines, researchers are often confronted with a number of results far beyond what they can realistically manage to read; when this happens, recommender systems can help, by pointing users to the most valuable sources of information. In the course of a long-term research project, research into one area can extend over se...

Graphical interfaces and interactive visualisations are typical mediators between human users and data analytics systems. HCI researchers and developers have to be able to understand both human needs and back-end data analytics. Participants of our tutorial will learn how visualisation and interface design can be combined with data analytics to pro...

An information landscape is commonly used to represent relatedness in large, high-dimensional datasets, such as text document collections. In this paper we present interactive metaphors, inspired in map reading and visual transitions, that enhance the landscape representation for the analysis of topical changes in dynamic text repositories. The goa...

Visualizations have a distinctive advantage when dealing with the information overload problem: since they are grounded in basic visual cognition, many people understand them. However, creating them requires specific expertise of the domain and underlying data to determine the right representation. Although there are rules that help generate them,...

Supporting individuals who lack experience or competence to evaluate an overwhelming amout of information such as from cultural, scientific and educational content makes recommender system invaluable to cope with the information overload problem. However, even recommended information scales up and users still need to consider large number of items....

The analysis of temporal relationships in large amounts of graph data has gained significance in recent years. In- formation providers such as journalists seek to bring order into their daily work when dealing with temporally distributed events and the network of entities, such as persons, organisations or locations, which are related to these even...

Linked Data has grown to become one of the largest available knowledge bases. Unfortunately, this wealth of data remains inaccessi-ble to those without in-depth knowledge of semantic technologies. We describe a toolchain enabling users without semantic technology back-ground to explore and visually analyse Linked Data. We demonstrate its applicabil...

Providing easy to use methods for visual analysis of Linked Data is often hindered by the complexity of semantic technologies. On the other hand, semantic information inherent to Linked Data provides opportunities to support the user in interactively analysing the data. This paper provides a demonstration of an interactive, Web-based visualisa-tion...

Linked Data has grown to become one of the largest available knowledge bases. Unfortunately, this wealth of data remains inaccessible to those without in-depth knowledge of semantic technologies. We describe a toolchain enabling users without semantic technology background to explore and visually analyse Linked Data. We demonstrate its applicabilit...

The proposed graph visualization method employs hierarchical aggregation of graph nodes and edges, and applies edge bundling on each hierarchy level to reduce clutter and improve the clarity of the representation. Our visualization system enables users to explore large, hierarchically aggregated graphs in a node-link based graph visualization. Hier...

Linked Open Data has grown into a large and recognised source of data, however its uptake and commercial exploitation does not yet reflect its potential value. Two factors with potential to contribute to the value of data are correlating previously uncorrelated data and providing answers based on the data. We present a data-centric question answeri...

Research papers are published in various digital libraries, which deploy their own meta-models and technologies to manage, query, and analyze scientific facts therein. Commonly they only consider the meta-data provided with each article, but not the contents. Hence, reaching into the contents of publications is inherently a tedious task. On top of...

Research depends to a large degree on the availability and quality of primary research data, i.e., data generated through experiments and evaluations. While the Web in general and Linked Data in particular provide a platform and the necessary technologies for sharing, managing and utilizing research data, an ecosystem supporting those tasks is stil...

Providing means for effectively accessing and exploring large textual data sets is a problem attracting attention of text mining and information visualization experts alike. Rapid growth of the data volume, heterogeneity and richness of metadata, and the dynamic nature of text repositories add to the complexity of the task. This chapter provides an...

Project managers increasingly rely on software support for monitoring status and development of projects gathered in large portfolios. The status of a project is characterized by a large number of mostly numerical parameters. Various chart visualisations are commonly used to express parameters, provide aggregation and support comparison. We propose...

Linked Data has become an essential part of the Semantic Web. A lot of Linked Data is already available in the Linked Open Data cloud, which keeps growing due to an influx of new data from research and open government activities. However, it is still quite difficult to access this wealth of semantically enriched data directly without having in-dept...

Scientific publications constitute an extremely valuable body of knowledge and can be seen as the roots of our civilisation. However, with the exponential growth of written publications, comparing facts and findings between different research groups and communities becomes nearly impossible. In this paper, we present a conceptual approach and a fir...

Incrementally computed information landscapes are an effective means to visualize longitudinal changes in large document repositories. Resembling tectonic processes in the natural world, dynamic rendering reflects both long-term trends and short-term fluctuations in such repositories. To visualize the rise and decay of topics, the mapping algorithm...

Ontology alignment is the process of mapping related concepts from different ontologies. A lot of research effort has been invested in development of algorithmic methods supporting automatic discovery of mappings between ontological concepts. However, automatic alignment remains potentially prone to errors especially with large real-world ontologie...

This paper collates eight expert opinions about Knowledge Visualization, what it is and what it should be. An average of 581 words long, topics span from representation, storytelling and criticizing the lack of theory, to communication, analytics for the masses and reasoning, to trendy Visual Thinking and creativity beyond PowerPoint. These individ...

Semantic technologies are of paramount importance to the future Internet. The reuse and integration of semantically described resources, such as data or services, necessitates the bringing of ontologies into mutual agreement. Ontology alignment deals with the discovery of correspondences between concepts and relations from different ontologies. Ali...

Automatic generation of taxonomies can be useful for a wide area of applications. In our application scenario a topical hierarchy should be constructed reasonably fast from a large document collection to aid browsing of the data set. The hierarchy should also be used by the InfoSky projection algorithm to create an information landscape visualizati...

Classifiers can be used to automatically dispatch the abundance of newly created documents to recipients interested in particular topics. Identification of adequate training examples is essential for classification performance, but it may prove to be a challenging task in large document repositories. We propose a classifier hypothesis generation me...

This paper presents a technique for the visual analysis of topical shifts in dynamically changing textual archives. Our approach is based on the well-known information landscape metaphor, whereby topical changes are represented by changes in landscape topography. Incremental clustering and multi-dimensional scaling algorithms are periodically appli...

Knowledge discovery involves data driven processes where data is transformed and processed by various algorithms to identify new knowledge. KnowMiner is a service oriented framework providing a rich set of knowledge discovery functionalities with focus on text data sets. Complementing results of automatic machine analysis with the immense processin...

This paper presents a procedure to construct robust tax-onomies from natural language German encyclopedic text. Taxonomic relations are extracted through Hearst patterns, validated via search en-gines and incorporated into an base ontology. By verifying the relations using an external, web-based source of evidence, the procedure extracted an accura...

Services for increasing information quality in unstructured information are central to mostly all applications of information management. Service-oriented computing is a promising paradigm for embedding such intelligent services in different application scenarios and heterogeneous IT landscapes. In this paper we present our knowledge discovery fram...

Information technology has developed past its traditional focus on text-based data. The much-cited rapid growth of available information has been accompanied by a diversification of information types. Multimedia data is rapidly becoming the predominant form of information created, processed and distributed in many application domains.Multimedia dat...

Large collections of text documents are increasingly common, both in business and personal information environments. Tools from the field of information visualisation are being used to help users make sense of and extract useful knowledge from such collections. Flat text collections are often visualised using distance calculations between documents...

The domain of astronomy contributes a wealth of knowledge to the corpus of any general encyclopedia. Modern multimedia encyclopedias are capable of displaying complex, three-dimensional visualizations in real-time, enabling the integration of a planetarium, a virtual theater presenting astronomical facts in an educational and entertaining way. The...

In many application areas which deal with heterogeneous data sets temporal developments and topical relationships both play an important role. A number of visual representations have been developed which separately address each of these two aspects of the data. However, a simultaneous analysis of both aspects is also often required. In this paper w...

The MISTRAL system, a service oriented architecture for semantic extraction of multimedia data from meeting recordings is described shortly. It improves on other similar systems by extracting a variety of semantic metadata from one media type and integrating it with concepts derived from other media types, as well as by adding inference capabilitie...

The advent of electronic media enabling rapid publishing and instant access to news articles has vastly increased the working pace of the media industry. Press agencies can no longer afford to neglect plagiarisms formerly perceived as irrelevant because such acts instantly void the commercial value of original and potentially exclusive news article...

The archives of large national and international news agencies typically contain millions of articles featuring significant textual content and annotated metadata. Boolean queries and relevance ranked result lists have been traditional means of inquiry in such a context. This article presents an interface for query formulation and visual query anal...

Multimedia data has a rich and complex structure in terms of inter- and intra-document references. Its potential is severely limited unless effective methods for semantic extraction and semantic-based cross-media exploration and retrieval can be devised. Today's leading-edge techniques in this area are working well for low-level feature extraction...

Recent trends show that more and more digital cameras, video cam- eras and DVD recorders are sold and the number of emails and other messages sent increases each year. For example it is estimated that there will be nearly 300 million digital image capture devices in use worldwide through 2004, cap- turing about 29 billion digital pictures (12). Use...

It is no longer unusual for large document collections to contain many millions of documents. In order to manage this size of repository, it is often essential to structure the repository according to a thematic classification hierarchy. InfoSky is a system enabling users to explore such large, hierarchically structured document col-lections. Simil...

The WebRat is a light-weight, web-based retrieval, clustering and visualisation framework which can be used to quickly design and implement search solutions for a wide area of application domains. We have employed this framework to create a web meta search engine combined with an interactive visualisation and navigation toolkit. Based on the SVG gr...

This publication presents InfoSky, a system enabling exploration of large, hierarchically structured knowledge spaces. InfoSky employs a two-dimensional graphical representation with variable magnification, much like a real-world telescope, to visualise individual documents as stars, hierarchical structures as constellations, and the whole knowledg...

WebRat is an interactive system for visualising and refining and refining search result sets. Documents matching a query are dynamically clustered on the fly and visualised as a contour map of islands. Thematic clusters are built, analysed, and visualised in real time. Users can interactively explore the visualisation and refine queries by selectin...

This publication presents InfoSky, a system enabling exploration of large, hierarchically structured knowledge spaces. InfoSky employs a two-dimensional graphical representation with variable magnification, much like a real-world telescope, to visualise individual documents as stars, hierarchical structures as constellations, and the whole knowledg...

Today’s web search engines return very large result sets for query formulations consisting of few specific keywords. Results are presented as ranked lists containing textual description of found items. Such representations do not allow identification of topical clusters, and consequentially make it difficult for users to refine queries efficiently....

InfoSky is a system enabling users to explore large, hierarchically structured document collections. Similar to a real-world telescope, InfoSky employs a planar graphical representation with variable magnification. Documents of similar content are placed close to each other and are visualised as stars, forming clusters with distinct shapes. For gre...

The xFIND gatherer-broker architecture provides a wealth of metadata, which can be used to provide sophisticated search functionality. Local or remote documents are indexed and summaries and metadata are stored on an xFIND broker (server). An xFIND client can search a particular broker and access rich metadata for search result presentation, withou...

High quality software documentation is a substantial issue to understand software systems. Shorter time-to-market software cycles increase the importance of automatism to keep the documentation up to date. In this paper, we describe the automatic support of the software documentation process using a social semantic software approach. Therefore, we...

Challenges in Visual Analytics frequently involve massive repositories, which do not only contain a large number of information artefacts, but also a high number of relevant dimensions per artefact. Dimensionality reduction algorithms are commonly used to transform high-dimensional data into low-dimensional representations which are suitable for vi...

Recent trends in structure and content of global knowledge spaces present new chal-lenges to the field of Knowledge Discovery. Very large, highly structured repositories are in-creasingly replacing smaller, flat information spaces. Such repositories are often filled with multimedia documents, including image, audio and video data. This publication...

The InfoSky visual explorer is a system enabling users to interactively explore large, hierarchically structured document collections. Similar to a real-world telescope, InfoSky employs a planar graphical representation with variable magnification. Documents of similar content are placed close to each other and displayed as stars, while collections...