Edge bundling techniques cluster edges with similar attributes (i.e. similarity in direction and proximity) together to reduce the visual clutter. All edge bundling techniques to date implicitly or explicitly cluster groups of individual edges, or pa
rts of them, together based on these attributes. These clusters can result in ambiguous connections that do not exist in the data. Confluent drawings of networks do not have these ambiguities, but require the layout to be computed as part of the bundling process. We devise a new bundling method, Edge-Path bundling, to simplify edge clutter while greatly reducing ambiguities compared to previous bundling techniques. Edge-Path bundling takes a layout as input and clusters each edge along a weighted, shortest path to limit its deviation from a straight line. Edge-Path bundling does not incur independent edge ambiguities typically seen in all edge bundling methods, and the level of bundling can be tuned through shortest path distances, Euclidean distances, and combinations of the two. Also, directed edge bundling naturally emerges from the model. Through metric evaluations, we demonstrate the advantages of Edge-Path bundling over other techniques.
Dynamic networks can be challenging to analyze visually, especially if they span a large time range during which new nodes and edges can appear and disappear. Although it is straightforward to provide interfaces for visualization that represent multi
ple states of the network (i.e., multiple timeslices) either simultaneously (e.g., through small multiples) or interactively (e.g., through interactive animation), these interfaces might not support tasks in which disjoint timeslices need to be compared. Since these tasks are key for understanding the dynamic aspects of the network, understanding which interactive visualizations best support these tasks is important. We present the results of a series of laboratory experiments comparing two traditional approaches (small multiples and interactive animation), with a more recent approach based on interactive timeslicing. The tasks were performed on a large display through a touch interface. Participants completed 24 trials of three tasks with all techniques. The results show that interactive timeslicing brings benefit when comparing distant points in time, but less benefits when analyzing contiguous intervals of time.
Do algorithms for drawing graphs pass the Turing Test? That is, are their outputs indistinguishable from graphs drawn by humans? We address this question through a human-centred experiment, focusing on `small graphs, of a size for which it would be r
easonable for someone to choose to draw the graph manually. Overall, we find that hand-drawn layouts can be distinguished from those generated by graph drawing algorithms, although this is not always the case for graphs drawn by force-directed or multi-dimensional scaling algorithms, making these good candidates for Turing Test success. We show that, in general, hand-drawn graphs are judged to be of higher quality than automatically generated ones, although this result varies with graph size and algorithm.
This is the arXiv index for the electronic proceedings of GD 2019, which contains the peer-reviewed and revised accepted papers with an optional appendix. Proceedings (without appendices) are also to be published by Springer in the Lecture Notes in Computer Science series.
Uniform timeslicing of dynamic graphs has been used due to its convenience and uniformity across the time dimension. However, uniform timeslicing does not take the data set into account, which can generate cluttered timeslices with edge bursts and em
pty timeslices with few interactions. The graph mining filed has explored nonuniform timeslicing methods specifically designed to preserve graph features for mining tasks. In this paper, we propose a nonuniform timeslicing approach for dynamic graph visualization. Our goal is to create timeslices of equal visual complexity. To this end, we adapt histogram equalization to create timeslices with a similar number of events, balancing the visual complexity across timeslices and conveying more important details of timeslices with bursting edges. A case study has been conducted, in comparison with uniform timeslicing, to demonstrate the effectiveness of our approach.
For decades, researchers in information visualisation and graph drawing have focused on developing techniques for the layout and display of very large and complex networks. Experiments involving human participants have also explored the readability o
f different styles of layout and representations for such networks. In both bodies of literature, networks are frequently referred to as being large or complex, yet these terms are relative. From a human-centred, experiment point-of-view, what constitutes large (for example) depends on several factors, such as data complexity, visual complexity, and the technology used. In this paper, we survey the literature on human-centred experiments to understand how, in practice, different features and characteristics of node-link diagrams affect visual complexity.
Timeslices are often used to draw and visualize dynamic graphs. While timeslices are a natural way to think about dynamic graphs, they are routinely imposed on continuous data. Often, it is unclear how many timeslices to select: too few timeslices ca
n miss temporal features such as causality or even graph structure while too many timeslices slows the drawing computation. We present a model for dynamic graphs which is not based on timeslices, and a dynamic graph drawing algorithm, DynNoSlice, to draw graphs in this model. In our evaluation, we demonstrate the advantages of this approach over timeslicing on continuous data sets.
For large volumes of text data collected over time, a key knowledge discovery task is identifying and tracking clusters. These clusters may correspond to emerging themes, popular topics, or breaking news stories in a corpus. Therefore, recently there
has been increased interest in the problem of clustering dynamic data. However, there exists little support for the interactive exploration of the output of these analysis techniques, particularly in cases where researchers wish to simultaneously explore both the change in cluster structure over time and the change in the textual content associated with clusters. In this paper, we propose a model for tracking dynamic clusters characterized by the evolutionary events of each cluster. Motivated by this model, the TextLuas system provides an implementation for tracking these dynamic clusters and visualizing their evolution using a metro map metaphor. To provide overviews of cluster content, we adapt the tag cloud representation to the dynamic clustering scenario. We demonstrate the TextLuas system on two different text corpora, where they are shown to elucidate the evolution of key themes. We also describe how TextLuas was applied to a problem in bibliographic network research.
Analysts and social scientists in the humanities and industry require techniques to help visualize large quantities of microblogging data. Methods for the automated analysis of large scale social media data (on the order of tens of millions of tweets
) are widely available, but few visualization techniques exist to support interactive exploration of the results. In this paper, we present extended descriptions of ThemeCrowds and SentireCrowds, two tag-based visualization techniques for this data. We subsequently introduce a new list equivalent for both of these techniques and present a number of case studies showing them in operation. Finally, we present a formal user study to evaluate the effectiveness of these list interface equivalents when comparing them to ThemeCrowds and SentireCrowds. We find that discovering topics associated with areas of strong positive or negative sentiment is faster when using a list interface. In terms of user preference, multilevel tag clouds were found to be more enjoyable to use. Despite both interfaces being usable for all tested tasks, we have evidence to support that list interfaces can be more efficient for tasks when an appropriate ordering is known beforehand.
