Making machine intelligence less scary for criminal analysts : reflections on designing a visual comparative case analysis tool
2018-09, Jentner, Wolfgang, Sacha, Dominik, Stoffel, Florian, Ellis, Geoffrey, Zhang, Leishi, Keim, Daniel A.
A fundamental task in criminal intelligence analysis is to analyze the similarity of crime cases, called comparative case analysis (CCA), to identify common crime patterns and to reason about unsolved crimes. Typically, the data are complex and high dimensional and the use of complex analytical processes would be appropriate. State-of-the-art CCA tools lack flexibility in interactive data exploration and fall short of computational transparency in terms of revealing alternative methods and results. In this paper, we report on the design of the Concept Explorer, a flexible, transparent and interactive CCA system. During this design process, we observed that most criminal analysts are not able to understand the underlying complex technical processes, which decrease the users’ trust in the results and hence a reluctance to use the tool. Our CCA solution implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed visual analytics workflow iteratively supports the interpretation of the results of clustering with the respective feature relations, the development of alternative models, as well as cluster verification. The visualizations offer an understandable and usable way for the analyst to provide feedback to the system and to observe the impact of their interactions. Expert feedback confirmed that our user-centered design decisions made this computational complexity less scary to criminal analysts.
Identifying Patterns and Anomalies within Spatiotemporal Water Sampling Data
2018, Piljek, Isabel, Dehn, Giuliana, Frauendorf, Jannik, Salem, Ziad, Niyazbayev, Yerzhan, Buchmüller, Juri F., Cakmak, Eren, Jentner, Wolfgang, Stoffel, Florian, Keim, Daniel A.
This paper presents our solution to the Mini Challenge 2 (MC2) of the VAST Challenge 2018. We will analyze the provided data set and introduce our visualization tool, which was implemented and tailored to the tasks given by MC2. The tool combines the power of stream graphs, innovative glyph visualizations, box plots, sparklines, heat maps and cross-filter strategies. It allows identifying patterns and anomalies within the provided data set.
DeepClouds : Stereoscopic 3D Wordle based on Conical Spirals
2018, Jentner, Wolfgang, Stoffel, Florian, Jäckle, Dominik, Gärtner, Alexander, Keim, Daniel A.
Word clouds are a widely-used technique to visualize documents or collections of documents that arranged in a space-efficient 2D layout. Today’s state of the art in 3D computer graphics and its wide availability pose the question, how a 2D word cloud layout can be transferred into 3D space. In this paper, we discuss a prototypical 3D Wordle-based word cloud layout named DeepClouds that generates 3D word cloud layouts by introducing the depth of the position of words as an additional variable in the layout generation algorithm. Besides introducing the DeepClouds technique, we discuss emerging problems as well as possible future areas of research with respect to 3D word clouds.
Interactive Ambiguity Resolution of Named Entities in Fictional Literature
2017-07-04, Stoffel, Florian, Jentner, Wolfgang, Behrisch, Michael, Fuchs, Johannes, Keim, Daniel A.
Named entity recognition (NER) denotes the task to detect entities and their corresponding classes, such as person or location, in unstructured text data. For most applications, state of the art NER software is producing reasonable results. However, as a consequence of the methodological limitations and the well-known pitfalls when analyzing natural language data, the NER results are likely to contain ambiguities. In this paper, we present an interactive NER ambiguity resolution technique, which enables users to create (post-processing) rules for named entity recognition data based on the content and entity context of the analyzed documents. We specifically address the problem that in use-cases where ambiguities are problematic, such as the attribution of fictional characters with traits, it is often unfeasible to train models on custom data to improve state of the art NER software. We derive an iterative process model for improving NER results, show an interactive NER ambiguity resolution prototype, illustrate our approach with contemporary literature, and discuss our work and future research.
Minions, Sheep, and Fruits : Metaphorical Narratives to Explain Artificial Intelligence and Build Trust
2018, Jentner, Wolfgang, Sevastjanova, Rita, Stoffel, Florian, Keim, Daniel A., Bernard, Jürgen, El-Assady, Mennatallah
Advanced artificial intelligence models are used to solve complex real-world problems across different domains. While bringing along the expertise for their specific domain problems, users from these various application fields often do not readily understand the underlying artificial intelligence models. The resulting opacity implicates a low level of trust of the domain expert, leading to an ineffective and hesitant usage of the models. We postulate that it is necessary to educate the domain experts to prevent such situations. Therefore, we propose the metaphorical narrative methodology to transitively conflate the mental models of the involved modeling and domain experts. Metaphorical narratives establish an uncontaminated, unambiguous vocabulary that simplifies and abstracts the complex models to explain their main concepts. Elevating the domain experts in their methodological understanding results in trust building and an adequate usage of the models. To foster the methodological understanding, we follow the Visual Analytics paradigm that is known to provide an effective interface for the human and the machine. We ground our proposed methodology on different application fields and theories, detail four successfully applied metaphorical narratives, and discuss important aspects, properties, and pitfalls.
A Visual Analytics Approach for Crime Signature Generation and Exploration
2016, Jentner, Wolfgang, Ellis, Geoffrey, Stoffel, Florian, Sacha, Dominik, Keim, Daniel A.
The exploration of volumes of crime reports is a tedious task in crime intelligence analysis, given the largely unstructured nature of the crime descriptions. This paper describes a Visual Analytics approach for crime signature exploration that tightly integrates automated event sequence extraction and signature mining with interactive visualization. We describe the major components of our analysis pipeline — crime concept/event extraction, crime sequence mining, and interactive visualization. We illustrate its applicability with a real world use case. Finally, we discuss current problems, future plans, and open challenges in our development of a solution that incorporates automated event pattern mining with human expert feedback.