Quantifying the Visual Impact of Classification Boundaries in Choropleth Maps

Measuring the Effectiveness of Static Maps to Communicate Changes Over Time

Both in digital and print media, it is common to use static maps to show the evolution of values in various regions over time. The ability to communicate local or global trends, while reducing the cognitive load on readers, is of vital importance for an audience that is not always well versed in map interpretation. This study aims to measure the efficiency of four static maps (choropleth, tile grid map and their banded versions) to test their usefulness in presenting changes over time from a user experience perspective. We first evaluate the effectiveness of these map types by quantitative performance analysis (time and success rates). In a second phase, we gather qualitative data to detect which type of map favors decision-making. On a quantitative level, our results show that certain types of maps work better to show global trends, while other types are more useful when analyzing regional trends or detecting the regions that fit a specific pattern. On a qualitative level, those representations which are already familiar to the user are often better valued despite having lower measured success rates.

A survey of urban visual analytics: Advances and future directions

Developing effective visual analytics systems demands care in characterization of domain problems and integration of visualization techniques and computational models. Urban visual analytics has already achieved remarkable success in tackling urban problems and providing fundamental services for smart cities. To promote further academic research and assist the development of industrial urban analytics systems, we comprehensively review urban visual analytics studies from four perspectives. In particular, we identify 8 urban domains and 22 types of popular visualization, analyze 7 types of computational method, and categorize existing systems into 4 types based on their integration of visualization techniques and computational models. We conclude with potential research directions and opportunities.

A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in reusing existing labels from similar application domains. Transfer Learning is intended to relax this assumption by modeling relationships between domains, and is often applied in deep learning applications to reduce the demand for labeled data and training time. Despite recent advances in exploring deep learning models with visual analytics tools, little work has explored the issue of explaining and diagnosing the knowledge transfer process between deep learning models. In this paper, we present a visual analytics framework for the multi-level exploration of the transfer learning processes when training deep neural networks. Our framework establishes a multi-aspect design to explain how the learned knowledge from the existing model is transferred into the new learning task when training deep neural networks. Based on a comprehensive requirement and task analysis, we employ descriptive visualization with performance measures and detailed inspections of model behaviors from the statistical, instance, feature, and model structure levels. We demonstrate our framework through two case studies on image classification by fine-tuning AlexNets to illustrate how analysts can utilize our framework.

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics

Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks. However, the widely known modifiable areal unit problem within such aggregation processes can lead to perturbations in the network inputs. This issue can significantly destabilize the feature embeddings and the predictions - rendering deep networks much less useful for the experts. This paper approaches this challenge by leveraging unit visualization techniques that enable the investigation of many-to-many relationships between dynamically varied multi-scalar aggregations of urban traffic data and neural network predictions. Through regular exchanges with a domain expert, we design and develop a visual analytics solution that integrates 1) a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, 2) a Moran's I Scatterplot that provides local indicators of spatial association analysis, and 3) a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales. We evaluate our approach through a series of case studies involving a real-world dataset of Shenzhen taxi trips, and through interviews with domain experts. We observe that geographical scale variations have important impact on prediction performances, and interactive visual exploration of dynamically varying inputs and outputs benefit experts in the development of deep traffic prediction models.

Exploring the Sensitivity of Choropleths under Attribute Uncertainty

The choropleth map is an essential tool for spatial data analysis. However, the underlying attribute values of a spatial unit greatly influence the statistical analyses and map classification procedures when generating a choropleth map. If the attribute values incorporate a range of uncertainty, a critical task is determining how much the uncertainty impacts both the map visualization and the statistical analysis. In this paper, we present a visual analytics system that enhances our understanding of the impact of attribute uncertainty on data visualization and statistical analyses of these data. Our system consists of a parallel coordinates-based uncertainty specification view, an impact river and impact matrix visualization for region-based and simulation-based analysis, and a dual-choropleth map and t-SNE plot for visualizing the changes in classification and spatial autocorrelation over the range of uncertainty in the attribute values. We demonstrate our system through three use cases illustrating the impact of attribute uncertainty in geographic analysis.

Identifying Leadership Characteristics from Social Media Data during Natural Hazards using Personality Traits

With the availability of smart devices and affordable data plans, social media platforms have become the primary source of information dissemination across geographically dispersed users/locations. It has shown great potential across different application domains including event detection, opinion analysis, recommendation, and prediction. However, the process of extracting useful information from the collected voluminous social media data during natural hazards is a standing problem that needs significant attention from the research community. The fine-grained knowledge detailing users’ participation in information spreading could be advantageous in developing a reliable social network for the adverse events (Natural Hazards, Man-made attacks etc.). However, there has been no such findings related to identification of leader and their leadership characteristics associated with natural hazards in previous studies. We have collected 20.6 million tweets which were posted by 5.3 million users, during distinct devastating hazards namely - Floods, Hurricane, Earthquake and Typhoons. To achieve the goal, we divided our work in to three parts. Firstly, classify the collected crises data into four domains i.e resource, causality, news, and sympathy by employing deeper recurrent neural network model. Secondly, we used statistical physics of complex network to recognize local as well as global prominent leaders. At last, we curate leadership characteristics in terms of their big five personality traits and emotional traits. Our experimental, results find evidence that local leadership behaviour characteristics are significantly different from global potentials. Where as we also finds that some behaviour traits were certain to classified domains (resource, causality, news, and sympathy) and some were certain to hazard divisions, though emotional characteristics remained consistent. Later, we conclude that local potentials leaders have comparatively higher emotional strength. Furthermore, when the complete local network structure is unavailable, we find that the dynamic rank is reliable indexing proxy for local potentials. The current study, provide useful insight to understand how leadership characteristics are influenced to hazards, domains and centrality of users.