Wolfgang Jentner

Integrated visual analysis of patterns in time series and text data - Workflow and application to financial data analysis

In this article, we describe a workflow and tool that allows a flexible formation of hypotheses about text features and their combinations, which are significantly connected in time to quantitative phenomena observed in stock data. To support such an analysis, we combine the analysis steps of frequent quantitative and text-oriented data using an existing a priori method. First, based on heuristics, we extract interesting intervals and patterns in large time series data. The visual analysis supports the analyst in exploring parameter combinations and their results. The identified time series patterns are then input for the second analysis step, in which all identified intervals of interest are analyzed for frequent patterns co-occurring with financial news. An a priori method supports the discovery of such sequential temporal patterns. Then, various text features such as the degree of sentence nesting, noun phrase complexity, and the vocabulary richness, are extracted from the news items to obtain meta-patterns. Meta-patterns are defined by a specific combination of text features which significantly differ from the text features of the remaining news data. Our approach combines a portfolio of visualization and analysis techniques, including time, cluster, and sequence visualization and analysis functionality. We provide a case study and an evaluation on financial data where we identify important future work. The workflow could be generalized to other application domains such as data analysis of smart grids, cyber physical systems, or the security of critical infrastructure, where the data consist of a combination of quantitative and textual time series data.

Relating interesting quantitative time series patterns with text events and text features

In many application areas, the key to successful data analysis is the integrated analysis of heterogeneous data. One example is the financial domain, where time-dependent and highly frequent quantitative data (e.g., trading volume and price information) and textual data (e.g., economic and political news reports) need to be considered jointly. Data analysis tools need to support an integrated analysis, which allows studying the relationships between textual news documents and quantitative properties of the stock market price series. In this paper, we describe a workflow and tool that allows a flexible formation of hypotheses about text features and their combinations, which reflect quantitative phenomena observed in stock data. To support such an analysis, we combine the analysis steps of frequent quantitative and text-oriented data using an existing a-priori method. First, based on heuristics we extract interesting intervals and patterns in large time series data. The visual analysis supports the analyst in exploring parameter combinations and their results. The identified time series patterns are then input for the second analysis step, in which all identified intervals of interest are analyzed for frequent patterns co-occurring with financial news. An a-priori method supports the discovery of such sequential temporal patterns. Then, various text features like the degree of sentence nesting, noun phrase complexity, the vocabulary richness, etc. are extracted from the news to obtain meta patterns. Meta patterns are defined by a specific combination of text features which significantly differ from the text features of the remaining news data. Our approach combines a portfolio of visualization and analysis techniques, including time-, cluster- and sequence visualization and analysis functionality. We provide two case studies, showing the effectiveness of our combined quantitative and textual analysis work flow. The workflow can also be generalized to other application domains such as data analysis of smart grids, cyber physical systems or the security of critical infrastructure, where the data consists of a combination of quantitative and textual time series data.

Visual Comparative Case Analytics

Criminal Intelligence Analysis (CIA) faces a challenging task in handling high-dimensional data that needs to be investigated with complex analytical processes. State-of-the-art crime analysis tools do not fully support interactive data exploration and fall short of computational transparency in terms of revealing alternative results. In this paper we report our ongoing research into providing the analysts with such a transparent and interactive system for exploring similarities between crime cases. The system 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 (VA) workflow iteratively supports the interpretation of obtained clustering results, the development of alternative models, as well as cluster verification. The visualizations offer a usable way for the analyst to provide feedback to the system and to observe the impact of their interactions

Feature Alignment for the Analysis of Verbatim Text Transcripts

In the research of deliberative democracy, political scientists are interested in analyzing the communication models of discussions, debates, and mediation processes with the goal of extracting reoccurring discourse patterns from the verbatim transcripts of these conversations. To enhance the time-exhaustive manual analysis of such patterns, we introduce a visual analytics approach that enables the exploration and analysis of repetitive feature patterns over parallel text corpora using feature alignment. Our approach is tailored to the requirements of our domain experts. In this paper, we discuss our visual design and workflow, and we showcase the applicability of our approach using an experimental parallel corpus of political debates.

Making machine intelligence less scary for criminal analysts: reflections on designing a visual comparative case analysis tool

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.

A Concept for Consensus-based Ordering of Views

High-dimensional data poses a significant challenge for analysis, as patterns typically exist only in subsets of dimensions or records. A common approach to reveal patterns, such as meaningful structures or relationships, is to split the data and then to create a visual representation (views) for each data subset. This introduces the problem of ordering the views effectively because patterns can depend on the presented sequence. Existing methods provide metrics and heuristics to achieve an ordering of views based on their data characteristics. However, an effective ordering of subspace views is expected to rely on taskand data-dependent properties. Hence, heuristic-based ordering methods can be highly objective and not relevant to the task at hand, which is why the user involvement is key to find a meaningful ordering. We introduce a concept for a consensus-based ordering of views that learns to form sequences of subset views fitting the overall users’ needs. This concept allows users to decide on the ordering freely and accumulates their preference into a global view that reflects the consensus. We showcase and discuss this concept based on ordering colored tiles from the controversially discussed rainbow color map.

Interactive Ambiguity Resolution of Named Entities in Fictional Literature

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.