Visualization Tools
We have developed multiple software tools for data analysis and data visualization. Freely available tools are listed in the following.
Our interactive visual surveys of visualization techniques are available as online web-based systems. These tools support, for instance, identification of related work or open research questions which are uncovered so far. All contained visualization techniques were manually classified, and the tools provide features for searching and filtering.
Online Tools:
Relevant Research Areas and Projects:
SBGTool v2.0 is a novel web-based visual learning analytics (VLA) tool for grouping students who have similar learning outcomes. The SBGTool v2.0 can assist teachers with grouping efficiently by providing multiple visualizations in an interactive platform. Teachers can use the suggested VLA tools to compare groups of students with similar learning activities, as well as individual students; find the most difficult and easiest subjects; explore and understand students’ learning outcomes; find the relationship between students’ activity and success, and maximize the collaborative learning potential in their classroom.
Source Code:
Relevant Research Areas and Projects:
FeatureEnVi is a visual analytics tool specifically designed to assist with the feature engineering process. In summary, our proposed tool helps users to choose the most important feature, to transform the original features into powerful alternatives, and to experiment with different feature generation combinations. The final outcome is the extraction of heavily engineered features, evaluated by multiple validation metrics.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
VisEvol is a visual analytics tool that supports interactive exploration of hyperparameters and intervention in this evolutionary procedure. In summary, our proposed tool helps the user to generate new models through evolution and eventually explore powerful hyperparameter combinations in diverse regions of the extensive hyperparameter space. The outcome is a voting ensemble (with equal rights) that boosts the final predictive performance.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
StackGenVis assists users in dynamically adapting performance metrics, managing data instances, selecting the most important features for a given data set, choosing a set of top-performant and diverse algorithms, and measuring the predictive performance. In consequence, our proposed tool helps users to decide between distinct models and to reduce the complexity of the resulting stack by removing overpromising and underperforming models.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
t-viSNE is an interactive tool for the visual exploration of multidimensional data projections produced by the well-known dimensionality reduction algorithm called t-SNE. Our tool enables analysts to inspect different aspects of their accuracy and meaning, such as the effects of hyperparameters, distance and neighborhood preservation, densities and costs of specific neighborhoods, and the correlations between dimensions and visual patterns.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
Topics2Themes is a tool for interactive computer-assisted argument extraction which allows the user to explore the output of a topic modeling algorithm and define themes recurring in text data using an interactive visual interface.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
MVN-Reduce is a tool for exploring multidimensional data with a dimensionality reduction approach that takes both attribute- and edge-based similarities between the data points in consideration.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
StanceXplore is a tool for interactive exploration of stance in social media using coordinated multiple views including user-defined topics, content similarity and dissimilarity, and geographical and temporal distribution.
Online Tool:
Source Code:
Relevant Research Areas and Projects:
DoSVis ("Document Stance Visualization") is a tool for representing the results of stance classification (including multiple categories and category combinations such as HYPOTHETICALS and PREDICTION) in longer individual documents, e.g., books and business reports.
Online Tool:
Relevant Research Areas and Projects:
As part of our collaboration with HCI researchers, we developed a tool for visually representing excitement detected using wearable devices, with the data for a single or multiple persons incoming in a streaming fashion. The tool provides several alternatives for the visual encoding of excitement values and it also supports dynamic layout of the persons' representations based on a force-based approach.
Online Tool:
Relevant Research Areas and Projects:
PAL ("Pre-annotation and Active Learning") is a natural language processing tool aimed to simplify the annotation process for text data. The output of pre-annotation is provided in the format used by the well-known annotation tool BRAT.
Source Code:
Relevant Research Areas and Projects: