Andreas Stoffel

Knowledge Generation Model for Visual Analytics

Visual analytics enables us to analyze huge information spaces in order to support complex decision making and data exploration. Humans play a central role in generating knowledge from the snippets of evidence emerging from visual data analysis. Although prior research provides frameworks that generalize this process, their scope is often narrowly focused so they do not encompass different perspectives at different levels. This paper proposes a knowledge generation model for visual analytics that ties together these diverse frameworks, yet retains previously developed models (e.g., KDD process) to describe individual segments of the overall visual analytic processes. To test its utility, a real world visual analytics system is compared against the model, demonstrating that the knowledge generation process model provides a useful guideline when developing and evaluating such systems. The model is used to effectively compare different data analysis systems. Furthermore, the model provides a common language and description of visual analytic processes, which can be used for communication between researchers. At the end, our model reflects areas of research that future researchers can embark on.

Document Cards: A Top Trumps Visualization for Documents

Finding suitable, less space consuming views for a documents main content is crucial to provide convenient access to large document collections on display devices of different size. We present a novel compact visualization which represents the documents key semantic as a mixture of images and important key terms, similar to cards in a top trumps game. The key terms are extracted using an advanced text mining approach based on a fully automatic document structure extraction. The images and their captions are extracted using a graphical heuristic and the captions are used for a semi-semantic image weighting. Furthermore, we use the image color histogram for classification and show at least one representative from each non-empty image class. The approach is demonstrated for the IEEE InfoVis publications of a complete year. The method can easily be applied to other publication collections and sets of documents which contain images.

Visual Readability Analysis: How to Make Your Writings Easier to Read

We present a tool that is specifically designed to support a writer in revising a draft version of a document. In addition to showing which paragraphs and sentences are difficult to read and understand, we assist the reader in understanding why this is the case. This requires features that are expressive predictors of readability, and are also semantically understandable. In the first part of the paper, we, therefore, discuss a semiautomatic feature selection approach that is used to choose appropriate measures from a collection of 141 candidate readability features. In the second part, we present the visual analysis tool VisRA, which allows the user to analyze the feature values across the text and within single sentences. Users can choose between different visual representations accounting for differences in the size of the documents and the availability of information about the physical and logical layout of the documents. We put special emphasis on providing as much transparency as possible to ensure that the user can purposefully improve the readability of a sentence. Several case studies are presented that show the wide range of applicability of our tool. Furthermore, an in-depth evaluation assesses the quality of the measure and investigates how well users do in revising a text with the help of the tool.

Rolled-out Wordles: A Heuristic Method for Overlap Removal of 2D Data Representatives

When representing 2D data points with spacious objects such as labels, overlap can occur. We present a simple algorithm which modifies the (Mani‐) Wordle idea with scan‐line based techniques to allow a better placement. We give an introduction to common placement techniques from different fields and compare our method to these techniques w.r.t. euclidean displacement, changes in orthogonal ordering as well as shape and size preservation. Especially in dense scenarios our method preserves the overall shape better than known techniques and allows a good trade‐off between the other measures. Applications on real world data are given and discussed.

State-of-the-Art Report of Visual Analysis for Event Detection in Text Data Streams

Event detection from text data streams has been a popular research area in the past decade. Recently, the evolution of microblogging and social network services opens up great opportunities for various kinds of knowledge-based intelligence activities which require tracking of real-time events. In a sense, visualizations in combination with analytical processes could be a viable method for such tasks because it can be used to analyze the sheer amounts of text streams. However, data analysts and visualization experts often face grand challenges stemming out of the ill-defined concept of event and various kinds of textual data. As a result, we have few guidelines on how to build successful visual analysis tools that can handle specific event types and diverse textual data sources. Our goal is to take the first step towards answering the question by organizing insights from prior research studies on event detection and visual analysis. In the scope of this report, we summarize the evolution of event detection in combination with visual analysis over the past 14 years and provide an overview of the state-of-the-art methods. Our investigation sheds light on various kinds of research areas that can be the most beneficial to the field of visual text event analytics.

Processing online news streams for large-scale semantic analysis

While Internet has enabled us to access a vast amount of online news articles originating from thousands of different sources, the human capability to read all these articles has stayed rather constant. Usually, the publishing industry takes over the role of filtering this enormous amount of information and presenting it in an appropriate way to the group of their subscribers. In this paper, the semantic analysis of such news streams is discussed by introducing a system that streams online news collected by the Europe Media Monitor to our proposed semantic news analysis system. Thereby, we describe in detail the emerging challenges and the corresponding engineering solutions to process incoming articles close to real-time. To demonstrate the use of our system, the case studies show a) temporal analysis of entities, such as institutions or persons, and b) their co-occurence in news articles.

Methods for compensating contrast effects in information visualization

Color, as one of the most effective visual variables, is used in many techniques to encode and group data points according to different features. Relations between features and groups appear as visual patterns in the visualization. However, optical illusions may bias the perception at the first level of the analysis process. For instance, in pixel‐based visualizations contrast effects make pixels appear brighter if surrounded by a darker area, which distorts the encoded metric quantity of the data points. Even if we are aware of these perceptual issues, our visual cognition system is not able to compensate these effects accurately. To overcome this limitation, we present a color optimization algorithm based on perceptual metrics and color perception models to reduce physiological contrast or color effects. We evaluate our technique with a user study and find that the technique doubles the accuracy of users comparing and estimating color encoded data values. Since the presented technique can be used in any application without adaption to the visualization itself, we are able to demonstrate its effectiveness on data visualizations in different domains.

Enhancing document structure analysis using visual analytics

During the last decade national archives, libraries, museums and companies started to make their records, books and files electronically available. In order to allow efficient access of this information, the content of the documents must be stored in database and information retrieval systems. State-of-the-art indexing techniques mostly rely on the information explicitly available in the text portions of documents. Documents usually contain a significant amount of implicit information such as their logical structure which is not directly accessible (unless the documents are available as well-structured XML-files) and is therefore not used in the search process. In this paper, a new approach for analyzing the logical structure of text documents is presented. The problem of state-of-the-art methods is that they have been developed for a particular type of documents and can only handle documents of that type. In most cases, adaptation and re-training for a different document type is not possible. Our proposed method allows an efficient and effective adaptation of the structure analysis process by combining state-of-the-art machine learning with novel interactive visualization techniques, allowing a quick adaptation of the structure analysis process to unknown document classes and new tasks without requiring a predefined training set.

Visual readability analysis: How to make your writings easier to read

We present a tool that is specifically designed to support a writer in revising a draft-version of a document. In addition to showing which paragraphs and sentences are difficult to read and understand, we assist the reader in understanding why this is the case. This requires features that are expressive predictors of readability, and are also semantically understandable. In the first part of the paper, we therefore discuss a semi-automatic feature selection approach that is used to choose appropriate measures from a collection of 141 candidate readability features. In the second part, we present the visual analysis tool VisRA, which allows the user to analyze the feature values across the text and within single sentences. The user can choose different visual representations accounting for differences in the size of the documents and the availability of information about the physical and logical layout of the documents. We put special emphasis on providing as much transparency as possible to ensure that the user can purposefully improve the readability of a sentence. Several case-studies are presented that show the wide range of applicability of our tool.

Document Thumbnails with Variable Text Scaling

Document reader applications usually offer an overview of the layout for each page as thumbnail views. Reading the text in these becomes impossible when the font size becomes very small. We improve the readability of these thumbnails using a distortion method, which retains a readable font size of interesting text while shrinking less interesting text further. In contrast to existing approaches, our method preserves the global layout of a page and is able to show context around important terms. We evaluate our technique and show application examples.