To design a pedestrian crossing area reasonably can be a demanding task for traffic planners. There are several challenges, including determining the appropriate dimensions, and ensuring that pedestrians are exposed to the least risks. Pedestrian safety is especially obscure to analyze, given that many people in Stockholm cross the street illegally by running against the red light. To cope with these challenges, computational approaches of trajectory data visual analytics can be used to support the analytical reasoning process. However, it remains an unexplored field regarding how to visualize and communicate the street-crossing spatio-temporal data effectively. Moreover, the rendering also needs to deal with a growing data size for a more massive number of people. This thesis proposes a web-based interactive visual analytics tool for pedestrians' street-crossing behavior under various flow rates. The visualization methodology is also presented, which is then evaluated to have achieved satisfying communication and rendering effectiveness for maximal 180 agents over 100 seconds. In terms of the visualization scenario, pedestrians either wait for the red light or cross the street illegally; all people can choose to stop by a buffer island before they finish crossing. The visualization enables the analysis under multiple flow rates for 1) pedestrian movement, 2) space utilization, 3) crossing frequency in time-series, and 4) illegal frequency. Additionally, to acquire the initial trajectory data, Optimal Reciprocal Collision Avoidance (ORCA) algorithm is engaged in the crowd simulation. Then different visualization techniques are utilized to comply with user demands, including map animation, data aggregation, and time-series graph. / Att konstruera ett gångvägsområde kan rimligen vara en krävande uppgift för trafikplanerare. Det finns flera utmaningar, bland annat att bestämma lämpliga dimensioner och se till att fotgängare utsätts för minst risker. Fotgängarnas säkerhet är särskilt obskyrlig att analysera, eftersom många människor i Stockholm korsar gatan olagligt genom att springa mot det röda ljuset. För att klara av dessa utmaningar kan beräkningsmetoder för bana data visuell analys användas för att stödja den analytiska resonemangsprocessen. Det är emellertid ett oexplorerat fält om hur man visualiserar och kommunicerar gataövergången spatio-temporal data effektivt. Dessutom måste rendering också hantera en växande datastorlek för ett mer massivt antal människor. Denna avhandling föreslår ett webbaserat interaktivt visuellt analysverktyg för fotgängares gatöverföring under olika flödeshastigheter. Visualiseringsmetoden presenteras också, som sedan utvärderas för att ha uppnått tillfredsställande kommunikation och effektivitet för maximal 180 agenter över 100 sekunder. Vad beträffar visualiseringsscenariot, väntar fotgängare antingen på det röda ljuset eller tvärs över gatan; alla människor kan välja att stanna vid en buffertö innan de slutar korsa. Visualiseringen möjliggör analysen under flera flödeshastigheter för 1) fotgängarrörelse, 2) rymdutnyttjande, 3) korsfrekvens i tidsserier och 4) olaglig frekvens. För att förvärva den ursprungliga bana-data är Optimal Reciprocal Collision Avoidance (ORCA) algoritmen förknippad med folkmassimuleringen. Därefter utnyttjas olika visualiseringstekniker för att uppfylla användarnas krav, inklusive kartanimering, dataaggregering och tidsserier.

After more than two decades, bullying and cyberbullying is still negatively impacting the lives of many of our youth and their families. The prevalence of the phenomenon is widespread and part of the everyday life activities. The impact of cyber aggression and violation can have severe consequences, up to the destruction of lives. While cyberbullying prevention programs exist, not much progress seems to have been made in the effort to combat the phenomenon. This research provides new insights into how to extract information by using existing research and online news articles, with the aim to create new or improve existing cyberbullying prevention efforts. The intent is to inform prevention programs.

Diaries are private documentations of people’s lives. They contain descriptions of events, thoughts, fears, and desires. While diaries are usually kept in private, published ones, such as the diary of Anne Frank, show that they bear the potential to give personal insight into events and into the emotional impact on their authors. We present a visualization tool that provides insight into the Bergen-Belsen memorial’s diary corpus, which consists of dozens of diaries written by concentration camp prisoners. We designed a calendar view that documents when authors wrote about concentration camp life. Different modes support quantitative and sentiment analyses, and we provide a solution for historians to create thematic concepts that can be used for searching and filtering for specific diary entries. The usage scenarios illustrate the importance of the tool for researchers and memorial visitors as well as for commemorating the Holocaust.

No description available.

The Multiset Sampler [Leman et al., 2009] has previously been deployed and developed for efficient sampling from complex stochastic processes. We extend the sampler and the surrounding theory to model selection problems. In such problems efficient exploration of the model space becomes a challenge since independent and ad-hoc proposals might not be able to jointly propose multiple parameter sets which correctly explain a new pro- posed model. In order to overcome this we propose a multiset on the model space to en- able efficient exploration of multiple model modes with almost no tuning. The Multiset Model Selection (MSMS) framework is based on independent priors for the parameters and model indicators on variables. We show that posterior model probabilities can be easily obtained from multiset averaged posterior model probabilities in MSMS. We also obtain typical Bayesian model averaged estimates for the parameters from MSMS. We apply our algorithm to linear regression where it allows easy moves between parame- ter modes of different models, and in probit regression where it allows jumps between widely varying model specific covariance structures in the latent space of a hierarchical model. The Storytelling algorithm [Kumar et al., 2006] constructs stories by discovering and con- necting latent connections between documents in a network. Such automated algorithms often do not agree with user's mental map of the data. Hence systems that incorporate feedback through visual interaction from the user are of immediate importance. We pro- pose a visual analytic framework in which such interactions are naturally incorporated in to the existing Storytelling algorithm through a redefinition of the latent topic space used in the similarity measure of the network. The document network can be explored us- ing the newly learned normalized topic weights for each document. Hence our algorithm augments the limitations of human sensemaking capabilities in large document networks by providing a collaborative framework between the underlying model and the user. Our formulation of the problem is a supervised topic modeling problem where the supervi- sion is based on relationships imposed by the user as a set of inequalities derived from tolerances on edge costs from inverse shortest path problem. We show a probabilistic modeling of the relationships based on auxiliary variables and propose a Gibbs sampling based strategy. We provide detailed results from a simulated data and the Atlantic Storm data set. / Ph. D.

Sensemaking tasks, such as reading many news articles to determine the truthfulness of a given claim, are difficult. These tasks require a series of iterative steps to first forage for relevant information and then synthesize this information into a final hypothesis. To assist with such tasks, visual analytics systems provide interactive visualizations of data to enable faster, more accurate, or more thorough analyses. For example, semantic interaction techniques leverage natural or intuitive interactions, like highlighting text, to automatically update the visualization parameters using machine learning. However, this process of using machine learning based on user interaction is not yet well defined. We begin our research efforts by developing a computational pipeline that models and captures how a system processes semantic interactions. We then expanded this model to denote specifically how each component of the pipeline supports steps of the Sensemaking Process. Additionally, we recognized a cognitive symmetry in how analysts consider data items (like news articles) and their attributes (such as terms that appear within the articles). To support this symmetry, we also modeled how to visualize and interact with data items and their attributes simultaneously. We built a testbed system and conducted a user study to determine which analytic tasks are best supported by such symmetry. Then, we augmented the testbed system to scale up to large data using semantic interaction foraging, a method for automated foraging based on user interaction. This experience enabled our development of design challenges and a corresponding future research agenda centered on semantic interaction foraging. We began investigating this research agenda by conducting a second user study on when to apply semantic interaction foraging to better match the analyst's Sensemaking Process. / Doctor of Philosophy / Sensemaking tasks such as determining the truthfulness of a claim using news articles are complex, requiring a series of steps in which the relevance of each piece of information within the articles is first determined. Relevant pieces of information are then combined together until a conclusion may be reached regarding the truthfulness of the claim. To help with these tasks, interactive visualizations of data can make it easier or faster to find or combine information together. In this research, we focus on leveraging natural or intuitive interactions, such organizing documents in a 2-D space, which the system uses to perform machine learning to automatically adjust the visualization to better support the given task. We first model how systems perform such machine learning based on interaction as well as model how each component of the system supports the user's sensemaking task. Additionally, we developed a model and accompanying testbed system for simultaneously evaluating both data items (like news articles) and their attributes (such as terms within the articles) through symmetrical visualization and interaction methods. With this testbed system, we devised and conducted a user study to determine which types of tasks are supported or hindered by such symmetry. We then combined these models to build an additional testbed system that implemented a searching technique to automatically add previously unseen, relevant pieces of information to the visualization. Using our experience in implementing this automated searching technique, we defined design challenges to guide future implementations, along with a research agenda to refine the technique. We also devised and conducted another user study to determine when such automated searching should be triggered to best support the user's sensemaking task.

With the rise of big data, it is becoming increasingly important to educate students about data analytics. In particular, students without a strong mathematical background usually have an unenthusiastic attitude towards high-dimensional data and find it challenging to understand relevant complex analytical methods, such as dimension reduction. In this thesis, we present an embodied approach for visual analytics designed to teach students exploring alternative 2D projections of high dimensional data points using weighted multidimensional scaling. We proposed a novel application, <i>Be the Data</i>, to explore the possibilities of using human's embodied resources to learn from high dimensional data. In our system, each student embodies a data point and the position of students in a physical space represents a 2D projection of the high-dimensional data. Students physically moves in a room with respect to others to interact with alternative projections and receive visual feedback. We conducted educational workshops with students inexperienced in relevant data analytical methods. Our findings indicate that the students were able to learn about high-dimensional data and data analysis process despite their low level of knowledge about the complex analytical methods. We also applied the same techniques into social meetings to explain social gatherings and facilitate interactions. / Master of Science

Human-AI interaction can improve overall performance, exceeding the performance that either humans or AI could achieve separately, thus producing a whole greater than the sum of the parts. Visual analytics enables collaboration between humans and AI through interactive visual interfaces. Semantic interaction is a design methodology to enhance visual analytics systems for sensemaking tasks. It is widely applied for sensemaking in high-stakes domains such as intelligence analysis and academic research. However, existing semantic interaction systems support collaboration between humans and traditional machine learning models only; they do not apply state-of-the-art deep learning techniques. The contribution of this work is the effective integration of deep neural networks into visual analytics systems with semantic interaction. More specifically, I explore how to redesign the semantic interaction pipeline to enable collaboration between human and deep learning models for sensemaking tasks. First, I validate that semantic interaction systems with pre-trained deep learning better support sensemaking than existing semantic interaction systems with traditional machine learning. Second, I integrate interactive deep learning into the semantic interaction pipeline to enhance inference ability in capturing analysts' precise intents, thereby promoting sensemaking. Third, I add semantic explanation into the pipeline to interpret the interactively steered deep learning model. With a clear understanding of DL, analysts can make better decisions. Finally, I present a neural design of the semantic interaction pipeline to further boost collaboration between humans and deep learning for sensemaking. / Doctor of Philosophy / Human AI interaction can harness the separate strengths of human and machine intelligence to accomplish tasks neither can solve alone. Analysts are good at making high-level hypotheses and reasoning from their domain knowledge. AI models are better at data computation based on low-level input features. Successful human-AI interactions can perform real-world, high-stakes tasks, such as issuing medical diagnoses, making credit assessments, and determining cases of discrimination. Semantic interaction is a visual methodology providing intuitive communications between analysts and traditional machine learning models. It is commonly utilized to enhance visual analytics systems for sensemaking tasks, such as intelligence analysis and scientific research. The contribution of this work is to explore how to use semantic interaction to achieve collaboration between humans and state-of-the-art deep learning models for complex sensemaking tasks. To do this, I first evaluate the straightforward solution of integrating the pretrained deep learning model into the traditional semantic interaction pipeline. Results show that the deep learning representation matches human cognition better than hand engineering features via semantic interaction. Next, I look at methods for supporting semantic interaction systems with interactive and interpretable deep learning. The new pipeline provides effective communication between human and deep learning models. Interactive deep learning enables the system to better capture users' intents. Interpretable deep learning lets users have a clear understanding of models. Finally, I improve the pipeline to better support collaboration using a neural design. I hope this work can contribute to future designs for the human-in-the-loop analysis with deep learning and visual analytics techniques.

No description available.

Acquérir et traiter des données est de moins en moins coûteux, à la fois en matériel et en temps, mais encore faut-il pouvoir les analyser et les interpréter malgré leur complexité. La dimensionnalité est un des aspects de cette complexité intrinsèque. Pour aider à interpréter et à appréhender ces données le recours à la visualisation est indispensable au cours du processus d’analyse. La projection représente les données sous forme d’un nuage de points 2D, indépendamment du nombre de dimensions. Cependant cette technique de visualisation souffre de distorsions dues à la réduction de dimension, ce qui pose des problèmes d’interprétation et de confiance. Peu d’études ont été consacrées à la considération de l’impact de ces artefacts, ainsi qu’à la façon dont des utilisateurs non-familiers de ces techniques peuvent analyser visuellement une projection. L’approche soutenue dans cette thèse repose sur la prise en compte interactive des artefacts, afin de permettre à des analystes de données ou des non-experts de réaliser de manière fiable les tâches d’analyse visuelle des projections. La visualisation interactive des proximités colore la projection en fonction des proximités d’origine par rapport à une donnée de référence dans l’espace des données. Cette technique permet interactivement de révéler les artefacts de projection pour aider à appréhender les détails de la structure sous-jacente aux données. Dans cette thèse, nous revisitons la conception de cette technique et présentons ses apports au travers de deux expérimentations contrôlées qui étudient l’impact des artefacts sur l’analyse visuelle des projections. Nous présentons également une étude de l’espace de conception d’une technique basée sur la métaphore de lentille et visant à s’affranchir localement des problématiques d’artefacts de projection. / The cost of data acquisition and processing has radically decreased in both material and time. But we also need to analyze and interpret the large amounts of complex data that are stored. Dimensionality is one aspect of their intrinsic complexity. Visualization is essential during the analysis process to help interpreting and understanding these data. Projection represents data as a 2D scatterplot, regardless the amount of dimensions. However, this visualization technique suffers from artifacts due to the dimensionality reduction. Its lack of reliability implies issues of interpretation and trust. Few studies have been devoted to the consideration of the impact of these artifacts, and especially to give feedbacks on how non-expert users can visually analyze projections. The main approach of this thesis relies on an taking these artifacts into account using interactive techniques, in order to allow data scientists or non-expert users to perform a trustworthy visual analysis of projections. The interactive visualization of the proximities applies a coloring of the original proximities relatives to a reference in the data-space. This interactive technique allows revealing projection artifacts in order to help grasping details of the underlying data-structure. In this thesis, we redesign this technique and we demonstrate its potential by presenting two controlled experiments studying the impact of artifacts on the visual analysis of projections. We also present a design-space based on the lens metaphor, in order to improve this technique and to locally visualize a projection free of artifacts issues.