2018, Bäumle, Benedikt, Boesecke, Ina, Buchmüller, Raphael, Metz, Yannick, Buchmüller, Juri F., Cakmak, Eren, Jentner, Wolfgang, Keim, Daniel A.

To solve VAST Mini Challenge 1, we build an interactive visualization tool that allows hypothesis testing and exploratory analysis of the data. The tool contains different visualizations for metadata and audio data analysis. To analyze the recorded bird calls, we trained a Gradient Boosting-classifier to distinguish different bird species. Our tool integrates these results and visualizes them in combination with additional data allowing the user to get context information and confirm the results.

2016, Sacha, Dominik, Boesecke, Ina, Fuchs, Johannes, Keim, Daniel A.

Visual Analytics (VA) is a collaborative process between human and computer, where analysts are performing numerous interactions and reasoning activities. This paper presents our current progress in developing a note taking environment (NTE) that can be plugged to any VA system. The NTE supports the analysis process on the one hand, and captures user interactions on the other hand. Our aim is to integrate human lower- (exploration) with higher- (verification) level analytic processes and to investigate those together related to further human factors, such as trust building. We conducted a user study to collect and investigate analytic provenance data. Our early results reveal that analysis strategies and trust building are very individual. However, we were able to identify significant correlations between trust levels and interactions of particular participants.