Publikationen

Hier finden Sie von Know-Center MitarbeiterInnen verfasste wissenschaftliche Publikationen

2017

Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph

Tags, Titles or Q & A: Choosing Content Descriptors for Visual Recommender Systems

Proceedings of the 28th ACM Conference on Hypertext and Social Media, ACM, Prague, Czech Republic, 2017

Konferenz
In today's digital age with an increasing number of websites, social/learning platforms, and different computer-mediated communication systems, finding valuable information is a challenging and tedious task, regardless from which discipline a person is. However, visualizations have shown to be effective in dealing with huge datasets: because they are grounded on visual cognition, people understand them and can naturally perform visual operations such as clustering, filtering and comparing quantities. But, creating appropriate visual representations of data is also challenging: it requires domain knowledge, understanding of the data, and knowledge about task and user preferences. To tackle this issue, we have developed a recommender system that generates visualizations based on (i) a set of visual cognition rules/guidelines, and (ii) filters a subset considering user preferences. A user places interests on several aspects of a visualization, the task or problem it helps to solve, the operations it permits, or the features of the dataset it represents. This paper concentrates on characterizing user preferences, in particular: i) the sources of information used to describe the visualizations, the content descriptors respectively, and ii) the methods to produce the most suitable recommendations thereby. We consider three sources corresponding to different aspects of interest: a title that describes the chart, a question that can be answered with the chart (and the answer), and a collection of tags describing features of the chart. We investigate user-provided input based on these sources collected with a crowd-sourced study. Firstly, information-theoretic measures are applied to each source to determine the efficiency of the input in describing user preferences and visualization contents (user and item models). Secondly, the practicability of each input is evaluated with content-based recommender system. The overall methodology and results contribute methods for design and analysis of visual recommender systems. The findings in this paper highlight the inputs which can (i) effectively encode the content of the visualizations and user's visual preferences/interest, and (ii) are more valuable for recommending personalized visualizations.
2016

Luzhnica Granit, Pammer-Schindler Viktoria, Fessl Angela, Mutlu Belgin, Veas Eduardo Enrique

Designing Generic Visualisations for Activity Log Data

Workshop on Awareness and Reflection in Technology Enhanced Learning (ARTEL16), CEUR-WS, Lyon, 2016

Konferenz
Especially in lifelong or professional learning, the picture of a continuous learning analytics process emerges. In this proces s, het- erogeneous and changing data source applications provide data relevant to learning, at the same time as questions of learners to data cha nge. This reality challenges designers of analytics tools, as it req uires ana- lytics tools to deal with data and analytics tasks that are unk nown at application design time. In this paper, we describe a generic vi sualiza- tion tool that addresses these challenges by enabling the vis ualization of any activity log data. Furthermore, we evaluate how well parti cipants can answer questions about underlying data given such generic versus custom visualizations. Study participants performed better in 5 out of 10 tasks with the generic visualization tool, worse in 1 out of 1 0 tasks, and without significant difference when compared to the visuali zations within the data-source applications in the remaining 4 of 10 ta sks. The experiment clearly showcases that overall, generic, standalon e visualiza- tion tools have the potential to support analytical tasks suffi ciently well
2016

Mutlu Belgin, Sabol Vedran, Gursch Heimo, Kern Roman

From Data to Visualisations and Back: Selecting Visualisations Based on Data and System Design Considerations

arXiv, 2016

Konferenz
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 provide better visualisations. In the first of three parts, the participants will learn about visualisations and how to appropriately select them. In the second part, restrictions and opportunities associated with different data analytics systems will be discussed. In the final part, the participants will have the opportunity to develop visualisations and interface designs under given scenarios of data and system settings.
2015

Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph

VizRec: Recommending Personalized Visualizations

ACM Transactions on Interactive Intelligent Systems (TiiS) - Special Issue on Human Interaction with Artificial Advice Givers, ACM, 2015

Journal
Visualizations have a distinctive advantage when dealing with the information overload problem: since theyare grounded in basic visual cognition, many people understand them. However, creating the appropriaterepresentation requires specific expertise of the domain and underlying data. Our quest in this paper is tostudy methods to suggest appropriate visualizations autonomously. To be appropriate, a visualization hasto follow studied guidelines to find and distinguish patterns visually, and encode data therein. Thus, a visu-alization tells a story of the underlying data; yet, to be appropriate, it has to clearly represent those aspectsof the data the viewer is interested in. Which aspects of a visualization are important to the viewer? Canwe capture and use those aspects to recommend visualizations? This paper investigates strategies to recom-mend visualizations considering different aspects of user preferences. A multi-dimensional scale is used toestimate aspects of quality for charts for collaborative filtering. Alternatively, tag vectors describing chartsare used to recommend potentially interesting charts based on content. Finally, a hybrid approach combinesinformation on what a chart is about (tags) and how good it is (ratings). We present the design principlesbehindVizRec, our visual recommender. We describe its architecture, the data acquisition approach with acrowd sourced study, and the analysis of strategies for visualization recommendation
2015

Veas Eduardo Enrique, Mutlu Belgin, di Sciascio Maria Cecilia, Tschinkel Gerwald, Sabol Vedran

Visual Recommendations for Scientific and Cultural Content

IVAPP 2015, Berlin, 2015

Konferenz
Supporting individuals who lack experience or competence to evaluate an overwhelming amout of informationsuch as from cultural, scientific and educational content makes recommender system invaluable to cope withthe information overload problem. However, even recommended information scales up and users still needto consider large number of items. Visualization takes a foreground role, letting the user explore possiblyinteresting results. It leverages the high bandwidth of the human visual system to convey massive amounts ofinformation. This paper argues the need to automate the creation of visualizations for unstructured data adaptingit to the user’s preferences. We describe a prototype solution, taking a radical approach considering bothgrounded visual perception guidelines and personalized recommendations to suggest the proper visualization.
2015

Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph, Sabol Vedran

VizRec: A Two-Stage Recommender System for Personalized Visualizations

ACM IUI, ACM, Atlanta, Georgia, USA, 2015

Konferenz
Identifying and using the information from distributed and heterogeneous information sources is a challenging task in many application fields. Even with services that offer welldefined structured content, such as digital libraries, it becomes increasingly difficult for a user to find the desired information. To cope with an overloaded information space, we propose a novel approach – VizRec– combining recommender systems (RS) and visualizations. VizRec suggests personalized visual representations for recommended data. One important aspect of our contribution and a prerequisite for VizRec are user preferences that build a personalization model. We present a crowd based evaluation and show how such a model of preferences can be elicited.
2015

Mutlu Belgin, Sabol Vedran

Visual Analysis of Scientific Content

STCSN E-LETTER ON SCIENCE 2.0, 2015

Konferenz
The steadily increasing amount of scientific publications demands for more powerful, user-oriented technologiessupporting querying and analyzing scientific facts therein. Current digital libraries that provide services to accessscientific content are rather closed in a way that they deploy their own meta-models and technologies to query and analysethe knowledge contained in scientific publications. The goal of the research project CODE is to realize a framework basedon Linked Data principles which aims to provide methods for federated querying within scientific data, and interfacesenabling user to easily perform exploration and analysis tasks on received content. The main focus in this paper lieson the one hand on extraction and organization of scientific facts embedded in publications and on the other hand on anintelligent framework facilitating search and visual analysis of scientific facts through suggesting visualizations appropriatefor the underlying data.
2015

Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph, Sabol Vedran

Towards a Recommender Engine for Personalized Visualizations

UMAP, 2015

Konferenz
isualizations have a distinctive advantage when dealing with the information overload problem: being grounded in basic visual cognition, many people understand visualizations. However, when it comes to creating them, it requires specific expertise of the domain and underlying data to determine the right representation. Although there are rules that help generate them, the results are too broad as these methods hardly account for varying user preferences. To tackle this issue, we propose a novel recommender system that suggests visualizations based on (i) a set of visual cognition rules and (ii) user preferences collected in Amazon-Mechanical Turk. The main contribution of this paper is the introduction and the evaluation of a novel approach called VizRec that is able suggest an optimal list of top-n visualizations for heterogeneous data sources in a personalized manner.
2015

Tschinkel Gerwald, di Sciascio Maria Cecilia, Mutlu Belgin, Sabol Vedran

The Recommendation Dashboard: A System to Visualise and Organise Recommendations

Proceedings of the 19th International Conference on Information Visualisation (IV2015), 2015

Konferenz
Recommender systems are becoming common tools supportingautomatic, context-based retrieval of resources.When the number of retrieved resources grows large visualtools are required that leverage the capacity of humanvision to analyse large amounts of information. Weintroduce a Web-based visual tool for exploring and organisingrecommendations retrieved from multiple sourcesalong dimensions relevant to cultural heritage and educationalcontext. Our tool provides several views supportingfiltering in the result set and integrates a bookmarkingsystem for organising relevant resources into topic collections.Building upon these features we envision a systemwhich derives user’s interests from performed actions anduses this information to support the recommendation process.We also report on results of the performed usabilityevaluation and derive directions for further development.
2014

Mutlu Belgin, Tschinkel Gerwald, Veas Eduardo Enrique, Sabol Vedran, Stegmaier Florian, Granitzer Michael

Suggesting visualisations for published data

Information Visualization Theory and Applications (IVAPP), 2014 International Conference on, IEEE, 2014

Konferenz
Research papers are published in various digital libraries, which deploy their own meta-models and tech-nologies to manage, query, and analyze scientific facts therein. Commonly they only consider the meta-dataprovided with each article, but not the contents. Hence, reaching into the contents of publications is inherentlya tedious task. On top of that, scientific data within publications are hardcoded in a fixed format (e.g. tables).So, even if one manages to get a glimpse of the data published in digital libraries, it is close to impossibleto carry out any analysis on them other than what was intended by the authors. More effective querying andanalysis methods are required to better understand scientific facts. In this paper, we present the web-basedCODE Visualisation Wizard, which provides visual analysis of scientific facts with emphasis on automatingthe visualisation process, and present an experiment of its application. We also present the entire analyticalprocess and the corresponding tool chain, including components for extraction of scientific data from publica-tions, an easy to use user interface for querying RDF knowledge bases, and a tool for semantic annotation ofscientific data set
2014

Sabol Vedran, Tschinkel, Veas Eduardo Enrique, Mutlu Belgin, Granitzer Michael

Discovery and visual analysis of linked data for humans

International Semantic Web Conference, Springer, Cham, 2014

Konferenz
Linked Data has grown to become one of the largest availableknowledge bases. Unfortunately, this wealth of data remains inaccessi-ble to those without in-depth knowledge of semantic technologies. Wedescribe a toolchain enabling users without semantic technology back-ground to explore and visually analyse Linked Data. We demonstrateits applicability in scenarios involving data from the Linked Open DataCloud, and research data extracted from scientific publications. Our fo-cus is on the Web-based front-end consisting of querying and visuali-sation tools. The performed usability evaluations unveil mainly positiveresults confirming that the Query Wizard simplifies searching, refiningand transforming Linked Data and, in particular, that people using theVisualisation Wizard quickly learn to perform interactive analysis taskson the resulting Linked Data sets. In making Linked Data analysis ef-fectively accessible to the general public, our tool has been integratedin a number of live services where people use it to analyse, discover anddiscuss facts with Linked Data.
2014

Tschinkel Gerwald, Veas Eduardo Enrique, Mutlu Belgin, Sabol Vedran

Using semantics for interactive visual analysis of linked open data

Proceedings of the 2014 International Conference on Posters & Demonstrations Track-Volume 1272, CEUR-WS. org, 2014

Konferenz
Providing easy to use methods for visual analysis of LinkedData is often hindered by the complexity of semantic technologies. Onthe other hand, semantic information inherent to Linked Data providesopportunities to support the user in interactively analysing the data. Thispaper provides a demonstration of an interactive, Web-based visualisa-tion tool, the “Vis Wizard”, which makes use of semantics to simplify theprocess of setting up visualisations, transforming the data and, most im-portantly, interactively analysing multiple datasets using brushing andlinking method
2014

Stegmaier Florian, Seifert Christin, Kern Roman, Höfler Patrick, Bayerl Sebastian, Granitzer Michael, Kosch Harald, Lindstaedt Stefanie , Mutlu Belgin, Sabol Vedran, Schlegel Kai

Unleashing semantics of research data

Specifying Big Data Benchmarks, Springer, Berlin, Heidelberg, 2014

Buch
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 still missing. The vision of the CODE project is the establishment of a sophisticated ecosystem for Linked Data. Here, the extraction of knowledge encapsulated in scientific research paper along with its public release as Linked Data serves as the major use case. Further, Visual Analytics approaches empower end users to analyse, integrate and organize data. During these tasks, specific Big Data issues are present.
Kontakt Karriere

Hiermit erkläre ich ausdrücklich meine Einwilligung zum Einsatz und zur Speicherung von Cookies. Weiter Informationen finden sich unter Datenschutzerklärung

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close