Robert Krüger

ScatterBlogs2: Real-Time Monitoring of Microblog Messages through User-Guided Filtering

The number of microblog posts published daily has reached a level that hampers the effective retrieval of relevant messages, and the amount of information conveyed through services such as Twitter is still increasing. Analysts require new methods for monitoring their topic of interest, dealing with the data volume and its dynamic nature. It is of particular importance to provide situational awareness for decision making in time-critical tasks. Current tools for monitoring microblogs typically filter messages based on user-defined keyword queries and metadata restrictions. Used on their own, such methods can have drawbacks with respect to filter accuracy and adaptability to changes in trends and topic structure. We suggest ScatterBlogs2, a new approach to let analysts build task-tailored message filters in an interactive and visual manner based on recorded messages of well-understood previous events. These message filters include supervised classification and query creation backed by the statistical distribution of terms and their co-occurrences. The created filter methods can be orchestrated and adapted afterwards for interactive, visual real-time monitoring and analysis of microblog feeds. We demonstrate the feasibility of our approach for analyzing the Twitter stream in emergency management scenarios.

TrajectoryLenses - a set-based filtering and exploration technique for long-term trajectory data

The visual analysis of spatiotemporal movement is a challenging task. There may be millions of routes of different length and shape with different origin and destination, extending over a long time span. Furthermore there can be various correlated attributes depending on the data domain, e.g. engine measurements for mobility data or sensor data for animal tracking. Visualizing such data tends to produce cluttered and incomprehensible images that need to be accompanied by sophisticated filtering methods. We present TrajectoryLenses, an interaction technique that extends the exploration lens metaphor to support complex filter expressions and the analysis of long time periods. Analysts might be interested only in movements that occur in a given time range, traverse a certain region, or end at a given area of interest (AOI). Our lenses can be placed on an interactive map to identify such geospatial AOIs. They can be grouped with set operations to create powerful geospatial queries. For each group of lenses, users can access aggregated data for different attributes like the number of matching movements, covered time, or vehicle performance. We demonstrate the applicability of our technique on a large, real‐world dataset of electric scooter tracks spanning a 2‐year period.

Integrating predictive analytics and social media

A key analytical task across many domains is model building and exploration for predictive analysis. Data is collected, parsed and analyzed for relationships, and features are selected and mapped to estimate the response of a system under exploration. As social media data has grown more abundant, data can be captured that may potentially represent behavioral patterns in society. In turn, this unstructured social media data can be parsed and integrated as a key factor for predictive intelligence. In this paper, we present a framework for the development of predictive models utilizing social media data. We combine feature selection mechanisms, similarity comparisons and model cross-validation through a variety of interactive visualizations to support analysts in model building and prediction. In order to explore how predictions might be performed in such a framework, we present results from a user study focusing on social media data as a predictor for movie box-office success.

VESPa: A Pattern-based Visual Query Language for Event Sequences

Movement data can often be enriched with additional information that enables analysts to ask new questions, for instance about POIs visited and meetings that imply interactions between persons. Information on spatiotemporal events such as visits or meetings can be especially valuable for digital forensics, marketing analysis, and urban planning. Most existing query languages for movement data, however, do not take that additional information into account. We address this gap by proposing VESPa, a pattern-based graphical query language to express, check, and refine hypotheses about spatio-temporal event sequences. Using VESPa, the analyst can sketch abstract assumptions and use the pattern to query the data for matches. The applicability of our approach is demonstrated in two case studies with different datasets. We also report on a small user study in which several construction and comprehension tasks were successfully solved in an interactive implementation

Towards Interaction Techniques for Social Media Data Exploration on Large High-Resolution Displays

Exploring large geolocated social media datasets is now an important task in many pursuits e.g. crisis response. Yet there is still a lack of effective methods to view and interact with large amounts spatially-disturbed user-generated content. In this work, we explore interaction techniques for an extended version of ScatterBlogs - an interactive application for exploring massive twitter datasets on large high-resolution displays. We designed an interaction technique that employs multiple tablets to enable multiple users to effectively manipulate geolocated twitter massages on a large screen. In a preliminary user study, we compared our technique with using a desktop computer. Results indicate that the technique offers superior performance and user experience. In future work, we will explore how our technique can enhance the user experience of interacting with analytics applications.

Engaging people to participate in data collection

Through smartphones and mobile internet connections, collecting data from a large number of users and sensors has become ordinary. Users share information not only through private messages, but also over public available services or in particular applications contributing to data collection projects. On one hand, sensors in modern smartphones enable us to collect a large amount of information without the need to directly interact with the user. On the other hand, users actively share all kinds of information in social networks. However, it is still challenging to motivate a large number of people to participate in collecting data when active contribution is needed. This is particularly critical, when the needed information is of personal nature. In this work, we discuss four approaches to actively encourage users to provide information. Furthermore, we present first results of an online survey evaluating which of the approaches would be appreciated by users to contribute to a health data collection.

A Visual Analytics Framework for Exploring Theme Park Dynamics

In 2015, the top 10 largest amusement park corporations saw a combined annual attendance of over 400 million visitors. Daily average attendance in some of the most popular theme parks in the world can average 44,000 visitors per day. These visitors ride attractions, shop for souvenirs, and dine at local establishments; however, a critical component of their visit is the overall park experience. This experience depends on the wait time for rides, the crowd flow in the park, and various other factors linked to the crowd dynamics and human behavior. As such, better insight into visitor behavior can help theme parks devise competitive strategies for improved customer experience. Research into the use of attractions, facilities, and exhibits can be studied, and as behavior profiles emerge, park operators can also identify anomalous behaviors of visitors which can improve safety and operations. In this article, we present a visual analytics framework for analyzing crowd dynamics in theme parks. Our proposed framework is designed to support behavioral analysis by summarizing patterns and detecting anomalies. We provide methodologies to link visitor movement data, communication data, and park infrastructure data. This combination of data sources enables a semantic analysis of who, what, when, and where, enabling analysts to explore visitor-visitor interactions and visitor-infrastructure interactions. Analysts can identify behaviors at the macro level through semantic trajectory clustering views for group behavior dynamics, as well as at the micro level using trajectory traces and a novel visitor network analysis view. We demonstrate the efficacy of our framework through two case studies of simulated theme park visitors.

Visual Interactive Map Matching

Map matching is the process of assigning observed geographic positions of vehicles and their trajectories to the actual road links in a road network. In this paper, we present Visual Interactive Map Matching, a visual analytics approach to fine-tune the data preprocessing and matching process. It is based on ST-matching, a state-of-the-art and easy-to-understand map matching algorithm. Parameters of the preprocessing step and algorithm can be optimized with immediate visual feedback. Visualizations show current matching issues and performance metrics on a map and in diagrams. Manual and computer-supported editing of the road network model leads to a refined alignment of trajectories and roads. We demonstrate our approach with large-scale taxi trajectory data. We show that optimizing the matching on a subsample results in considerably improved matching quality, also when later scaled to the full dataset. An optimized matching ensures data faithfulness and prevents misinterpretation when the matched data might be investigated in follow-up analysis.

Visual Querying of Semantically Enriched Movement Data

Visual data exploration is used to reveal unknown patterns that, however, need to be validated, refined, and extracted for a final presentation and reporting. We contribute VESPa, a pattern-based visual query language for event sequences. With VESPa, analysts can formulate hypotheses gained and query the data for matches. In an interative analysis loop the pattern can be altered with further restrictions to narrow down the result set. Our language allows for (1) hypothesis expression and refinement, (2) visual querying, and (3) knowledge externalization. We focus on semantically enrichend movement data, used in law enforcement, consumer, and traffic analysis. To evaluate the applicability we present two case studies as well as a user study consisting of comprehensive and composition tasks.

Data-driven exploration of real-time geospatial text streams

Geolocated social media data streams are challenging data sources due to volume, velocity, variety, and unorthodox vocabulary. However, they also are an unrivaled source of eye-witness accounts to establish remote situational awareness. In this paper we summarize some of our approaches to separate relevant information from irrelevant chatter using unsupervised and supervised methods alike. This allows the structuring of requested information as well as the incorporation of unexpected events into a common overview of the situation. A special focus is put on the interplay of algorithms, visualization, and interaction.