Nils B. Weidmann

Stefan Scholz, Nils B. Weidmann, Zachary C. Steinert-Threlkeld et al.

Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. This paper presents a two-level classification method that addresses this transparency problem. At the first stage, an image segmenter detects the objects present in the image and a feature vector is created from those objects. In the second stage, this feature vector is used as input for standard machine learning classifiers to discriminate between images. We apply this method to a new dataset of more than 140,000 images to detect which ones display political protest. This analysis demonstrates three advantages to this paper's approach. First, identifying objects in images improves transparency by providing human-understandable labels for the objects shown on an image. Second, knowing these objects enables analysis of which distinguish protest images from non-protest ones. Third, comparing the importance of objects across countries reveals how protest behavior varies. These insights are not available using conventional computer vision classifiers and provide new opportunities for comparative research.

Enes Yigitbas, Simon Gorissen, Nils Weidmann et al.

Modeling is a key activity in conceptual design and system design. Through collaborative modeling, end-users, stakeholders, experts, and entrepreneurs are able to create a shared understanding of a system representation. While the Unified Modeling Language (UML) is one of the major conceptual modeling languages in object-oriented software engineering, more and more concerns arise from the modeling quality of UML and its tool support. Among them, the limitation of the two-dimensional presentation of its notations and lack of natural collaborative modeling tools are reported to be significant. In this paper, we explore the potential of using Virtual Reality (VR) technology for collaborative UML software design by comparing it with classical collaborative software design using conventional devices (Desktop PC, Laptop). For this purpose, we have developed a VR modeling environment that offers a natural collaborative modeling experience for UML Class Diagrams. Based on a user study with 24 participants, we have compared collaborative VR modeling with conventional modeling with regard to efficiency, effectiveness, and user satisfaction. Results show that the use of VR has some disadvantages concerning efficiency and effectiveness, but the user's fun, the feeling of being in the same room with a remote collaborator, and the naturalness of collaboration were increased.

Nils Weidmann, Suganya Kannan, Anthony Anjorin

Managing models in a consistent manner is an important task in the field of Model-Driven Engineering (MDE). Although restoring and maintaining consistency is desired in general, recent work has pointed out that always strictly enforcing consistency at any point of time is often not feasible in real-world scenarios, and sometimes even contrary to what a user expects from a trustworthy MDE tool. The challenge of tolerating inconsistencies has been discussed from different viewpoints within and outside the modelling community, but there exists no structured overview of existing and current work in this regard. In this paper, we provide such an overview to help join forces tackling the unresolved problems of tolerating inconsistencies in MDE. We follow the standard process of a Systematic Literature Review (SLR) to point out what tolerance means, how it relates to uncertainty, which examples for tolerant software systems have already been discussed, and which benefits and drawbacks tolerating inconsistencies entails. Furthermore, we propose a tool-chain that helps conducting SLRs in computer science and also eases the reproduction of results. Relevant meta-data of the collected sources is uniformly described in a textual modelling language and exported to the graph database Neo4j to query aggregated information.

Nils Weidmann, Anthony Anjorin, James Cheney

In the field of Model-Driven Engineering, there exist numerous tools that support various consistency management operations including model transformation, synchronisation and consistency checking. The supported operations, however, typically run completely in the background with only input and output made visible to the user. We argue that this often reduces both understandability and controllability. As a step towards improving this situation, we present VICToRy, a debugger for model generation and transformation based on Triple Graph Grammars, a well-known rule-based approach to bidirectional transformation. In addition to a fine-grained, step-by-step, interactive visualisation, VICToRy enables the user to actively explore and choose between multiple valid rule applications thus improving control and understanding.