TrajectoryVis: a visual approach to explore movement trajectories

Environmental Science and …

A visualizaion framework for social activity-travel studies was proposed and implemented on the basis of existing social network moels and needs for GPS-based travel data mining. Four visulizaion tasks were identified to reveal spatiotemporal characteristics of individuals with different personal attibutes and social networks. Softwae constructs and algorithms were developed for visual construction and analysis of social networks, relaion typology, and influential factor identification. The final verification result shows that our visualization framework is effective to identify the social dimension of activiy-travel behavior.

We propose TrajGraph, a new visual analytics method, for studying urban mobility patterns by integrating graph modeling and visual analysis with taxi trajectory data. A special graph is created to store and manifest real traffic information recorded by taxi trajectories over city streets. It conveys urban transportation dynamics which can be discovered by applying graph analysis algorithms. To support interactive, multiscale visual analytics, a graph partitioning algorithm is applied to create region-level graphs which have smaller size than the original street-level graph. Graph centralities, including Pagerank and betweenness, are computed to characterize the time-varying importance of different urban regions. The centralities are visualized by three coordinated views including a node-link graph view, a map view and a temporal information view. Users can interactively examine the importance of streets to discover and assess city traffic patterns. We have implemented a fully working prototype of this approach and evaluated it using massive taxi trajectories of Shenzhen, China. TrajGraph's capability in revealing the importance of city streets was evaluated by comparing the calculated centralities with the subjective evaluations from a group of drivers in Shenzhen. Feedback from a domain expert was collected. The effectiveness of the visual interface was evaluated through a formal user study. We also present several examples and a case study to demonstrate the usefulness of TrajGraph in urban transportation analysis.

2016

Chae, Junghoon Ph.D., Purdue University, December 2016. Visual Analytics of Locationbased Social Networks for Decision Support. Major Professor: David S. Ebert. Recent advances in technology have enabled people to add location information to social networks called Location-Based Social Networks (LBSNs) where people share their communication and whereabouts not only in their daily lives, but also during abnormal situations, such as crisis events. However, since the volume of the data exceeds the boundaries of human analytical capabilities, it is almost impossible to perform a straightforward qualitative analysis of the data. The emerging field of visual analytics has been introduced to tackle such challenges by integrating the approaches from statistical data analysis and human computer interaction into highly interactive visual environments. Based on the idea of visual analytics, this research contributes the techniques of knowledge discovery in social media data for providing compr...

Big Data and Cognitive Computing

Social networking platforms connect people from all around the world. Because of their user-friendliness and easy accessibility, their traffic is increasing drastically. Such active participation has caught the attention of many research groups that are focusing on understanding human behavior to study the dynamics of these social networks. Oftentimes, perceiving these networks is hard, mainly due to either the large size of the data involved or the ineffective use of visualization strategies. This work introduces VizTract to ease the visual perception of complex social networks. VizTract is a two-level graph abstraction visualization tool that is designed to visualize both hierarchical and adjacency information in a tree structure. We use the Facebook dataset from the Social Network Analysis Project from Stanford University. On this data, social groups are referred as circles, social network users as nodes, and interactions as edges between the nodes. Our approach is to present a v...

Computer Graphics …, 2011

2008

In this paper, we introduce a so-called DyVT tool (Dynamic social network Visualization Tool) to support spatiotemporal knowledge visualization and discovery in dynamic social networks. The dynamic aspects of social networks refer to contextualized information such as spatial, temporal as well as users' personalized information. We also define an XML-based target language incorporating emerging formats like DyNetML, KML, and GraphML. It also provides means to express, store and interchange the dynamic aspects of complex dynamic social network data. Based on this language, users can animate and personalize spatiotemporal knowledge extracted from social network data like email threads or blogs. In addition, a Java based graphical user interface is also available to enable nonexperienced users to customize knowledge visualization easily. A mashup with Google maps for spatiotemporal visualization is provided. With this tool spatiotemporal knowledge on an IBM DB2 Mailing list database containing 69 mailing lists and 56389 mails altogether is well explored.

2009

Visualization plays an important role in social networks analysis to explore and investigate individual and groups behaviours. Therefore, different approaches have been proposed for managing networks patterns and structures according to the visualization purposes. This paper presents a method of social networks visualization devoted not only to analyse individual and group social networking but also aimed to stimulate the second-one. This method provides (using a hybrid visualization approach) both an egocentric as well as a global point of view. Indeed, it is devoted to explore the social network structure, to analyse social aggregations and/or individuals and their evolution. Moreover, it considers and integrates features such as real-time social network elements locations in local areas. Multidimensionality consists of social phenomena, their evolution during the time, their individual characterization, the elements social position, and their spatial location. The proposed method was evaluated using the Social Interaction Map (SIM) software module in the scenario of planning and managing a scientific seminars cycle. This method enables the analysis of the topics evolution and the participants' scientific interests changes using a temporal layers sequence for topics. This knowledge provides information for planning next conference and events, to extend and modify main topics and to analyse research interests trends.

2019

Origin-Destination (OD) datasets describe the movement of entities between different geographic locations over time, such as human migration, movement of animals or diseases, traffic movement, etc. Visualizing the spatio-temporal patterns underlying OD databases is a challenging task since it involves the study of flows between spatial locations (origins and destinations) in a temporal context. Resulting from a collaborative effort of computer scientists and social scientists, our new visualization tool, EvoFlows, combines and synchronizes two complementary views. The first one relies on a system for visualizing time series data, MultiStream, and highlights the temporal dimension of OD data. It depicts inflows and outflows as aggregated stacked time series. Relying on flow maps, the second one highlights the geographic dimension and magnitude of flows at a given time-stamp. Our approach allows the temporal and spatial exploration of the flows at different levels of detail through mu...

Proceedings of the 50th Hawaii International Conference on System Sciences (2017), 2017

Online social data is potentially a rich source of insight into human behavior, but the sheer size of these datasets requires specialized tools to facilitate social media research. Visual analytics tools are one promising approach, but calls have been made for more in-depth studies in specific application domains to contribute to the design of such tools. We conducted a formative study to better understand the needs of social media researchers, and created Lariat, a visual analytics tool that facilitates exploratory data analysis through integrated grouping and visualization of social media data. The design of Lariat was informed by the results of the formative study and sensemaking theory, both indicating that the exploratory processes require search, comparison, verification, and iterative refinement. Based on our results and the evaluation of Lariat, we identify a number of design implications for future visual analytics tools in this domain.

2020

Twitter provides a function called "trend" that presents popular words and hashtags. Typically, one trend word or hashtag is related to thousands of tweets. It is difficult to understand such thousands of tweets in a short time by using the standard sort methods and the standard display method provided by Twitter. Most of previous studies analyzed and visualized tweets by using text-based clustering methods. However, these methods suffer from the accuracy of clustering results, because a typical tweet has only poor textual information. This paper presents a Twitter trend analysis system that combines retweet clustering and timeseries visualization to allow users to understand flows of topics in a Twitter trend in a short time. This system also provides a list of effective legends and a display of individual tweets with photos in order for users to further understand topics in a trend. To illustrate the effectiveness of this system, this paper presents the results of experiments on the analysis of Twitter trends related to a popular sport event and a popular music program.