The quest for the ideal flow visualization reveals two major challenges: interactivity and accura... more The quest for the ideal flow visualization reveals two major challenges: interactivity and accuracy. Interactivity stands for explorative capabilities and real-time control. Accuracy is a prerequisite for every professional visu-alization in order to provide a reliable base for analysis of a data set. Geometric flow visualization has a long tradition and comes in very different flavors. Among these, stream, path and streak lines are known to be very useful for both 2D and 3D flows. Despite their importance in practice, appropriate algorithms suited for con-temporary hardware are rare. In particular, the adaptive construction of the different line types is not sufficiently studied. This work provides a profound representation and discussion of stream, path and streak lines. Two algo-rithms are proposed for efficiently and accurately generating these lines using modern graphics hardware. Each includes a scheme for adaptive time-stepping. The adaptivity for stream and path lines is ach...
A scatterplot is one of the most popular techniques used for visu-alizing multidimensional datase... more A scatterplot is one of the most popular techniques used for visu-alizing multidimensional datasets. However, if the number of data points is large, occlusion and overdraw problems occur. Thus, it will be difficult to visually differentiate these data points and their clusters. Motion is one of the strongest low-level perceptual cues to draw our visual system’s attention to a certain subset of data. In this paper, we present three approaches that use different motion con-cepts to improve the identification and separation of precomputed clusters in scatterplots. First, we present two techniques generating real motion effects by the use of flickering and by the use of differ-ent weaving patterns. Furthermore, we present a technique using mimic motion by the use of peripheral drift.
A scatterplot is one of the most popular techniques used for visualizing multidimensional dataset... more A scatterplot is one of the most popular techniques used for visualizing multidimensional datasets. However, if the number of data points is large, occlusion and overdraw problems occur. Thus, it will be difficult to visually differentiate these data points and their clusters. Motion is one of the strongest low-level perceptual cues to draw our visual system’s attention to a certain subset of data. In this paper, we present three approaches that use different motion concepts to improve the identification and separation of precomputed clusters in scatterplots. First, we present two techniques generating real motion effects by the use of flickering and by the use of different weaving patterns. Furthermore, we present a technique using mimic motion by the use of peripheral drift.
The following system description presents our approach to the detection of persuasion techniques ... more The following system description presents our approach to the detection of persuasion techniques in texts and images. The given task has been framed as a multi-label classification problem with the different techniques serving as class labels. The multi-label classification problem is one in which a list of target variables such as our class labels is associated with every input chunk and assumes that a document can simultaneously and independently be assigned to multiple labels or classes. In order to assign class labels to the given memes, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for token and sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps. To incorporate image features in the multi-modal setting, we rely on the pre-trained VGG-16 model architecture.
The following system description presents our approach to the detection of fake news in texts. Th... more The following system description presents our approach to the detection of fake news in texts. The given task has been framed as a multi-class classification problem. The multi-class classification problem is one in which a target variable such as the given class label is associated with every input chunk. In order to assign class labels to the given documents, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps.
Kurzfassung. Im Kontext der Genexpressionsanalyse haben sich parallele Koordinaten (PK) als ein h... more Kurzfassung. Im Kontext der Genexpressionsanalyse haben sich parallele Koordinaten (PK) als ein hilfreiches Werkzeug erwiesen. Ein hochdimensionaler Datensatz kann auf diese Weise in einem zweidimensionalen Datenraum dargestellt werden. Dabei wird die Anzahl der darstellbaren Dimensionen lediglich durch den horizontal verfugbaren Platz begrenzt und ermoglicht ein relativ leichtes Erkennen inharenter Zusammenhange innerhalb eines Kontextes. Neben den offensichtlichen Vorteilen sind jedoch auch die damit verbundenen Beschrankungen zu berucksichtigen. Durch Uberlagerung einzelner Linien kann diese Darstellung relativ schnell uberzeichnet werden und verliert in diesen Bereichen an Informationsgehalt. Daruber hinaus stellt sich die Detektion von Korrelationen uber mehrere Achsen als eine relativ schwierige Aufgabe dar. Um die Frequenz von Kantenzugen entlang der Koordinatenachsen zu erhalten, werden zur graphischen Darstellung Histogramme herangezogen, welche jeweils an den Koordinatenac...
The following system description presents our approach to the estimation of check-worthiness of t... more The following system description presents our approach to the estimation of check-worthiness of text chunks. The given task has been framed as a regression problem. In order predict a numerical value for a chunk we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps.
The information space, where information is generated, stored, exchanged and discussed, is not id... more The information space, where information is generated, stored, exchanged and discussed, is not idyllic but a space where campaigns of disinformation and destabilization are conducted. Such campaigns are subsumed under the terms “hybrid warfare” and “information warfare” (Woolley and Howard, 2017). In order to enable awareness of them, we propose an information state dashboard comprising various components/apps for data collection, analysis and visualization. The aim of the dashboard is to support an analyst in generating a common operational picture of the information space, link it with an operational picture of the physical space and, thus, contribute to overarching situational awareness. The dashboard is work in progress. However, a first prototype with components for exploiting elementary language statistics, keyword and metadata analysis, text classification and network analysis has been implemented. Further components, in particular, for event extraction and sentiment analysis...
2021 International Conference on Military Communication and Information Systems (ICMCIS)
The Internet has long since established itself as an indispensable source of information for both... more The Internet has long since established itself as an indispensable source of information for both organizations and individuals. The lack of social responsibility of many digital platforms, however, offers many incentives for various forms of abuse. Disinformation, propaganda and fake news are just a few examples. Among the actors of information campaigns, we find not only individuals but also state actors with a clear agenda. Often, such information campaigns make use of psychological and rhetorical methods to achieve their goals. The manipulation of information is a major challenge for our democracies. It also presents us with major technical problems to identify and assess risks arising from the dissemination of such information.The following system description presents our approach to the detection of misinformation on social media data, which is twofold. Initially, we subjected the given training data to an exploratory analysis to get an overview of the general structure. Then we framed the given task as a simpler classification problem. In order to distinguish between trusted and untrusted information, using BERT (Bidirectional Encoder Representations from Transformers) as a neural network architecture for sequence classification, we started with a pre-trained model for language representation. In a supervised training step we fine-tuned this model on the given classification task with the provided annotated data.In this paper we would like to discuss both the quality of the training data and the performance of the trained classifier to derive promising directions for future work.
This paper describes the design and implementation of an interactive walk-through of a reconstruc... more This paper describes the design and implementation of an interactive walk-through of a reconstructed German stronghold, the Dillenburg. The application is currently in use at the local museum. Applying technologies and algorithms primarily used for the development of realis-tic 3D computer games, we present a system that can be categorized as a Serious Gaming environment, a term that has recently come into existence. More specifically, it can be called a Cultural Heritage Game. With this pa-per we want to give a programmer’s view on the topic of interactive cultural heritage systems.
The quest for the ideal flow visualization reveals two major challenges: interactivity and accura... more The quest for the ideal flow visualization reveals two major challenges: interactivity and accuracy. Interactivity stands for explorative capabilities and real-time control. Accuracy is a prerequisite for every professional visu-alization in order to provide a reliable base for analysis of a data set. Geometric flow visualization has a long tradition and comes in very different flavors. Among these, stream, path and streak lines are known to be very useful for both 2D and 3D flows. Despite their importance in practice, appropriate algorithms suited for con-temporary hardware are rare. In particular, the adaptive construction of the different line types is not sufficiently studied. This work provides a profound representation and discussion of stream, path and streak lines. Two algo-rithms are proposed for efficiently and accurately generating these lines using modern graphics hardware. Each includes a scheme for adaptive time-stepping. The adaptivity for stream and path lines is ach...
A scatterplot is one of the most popular techniques used for visu-alizing multidimensional datase... more A scatterplot is one of the most popular techniques used for visu-alizing multidimensional datasets. However, if the number of data points is large, occlusion and overdraw problems occur. Thus, it will be difficult to visually differentiate these data points and their clusters. Motion is one of the strongest low-level perceptual cues to draw our visual system’s attention to a certain subset of data. In this paper, we present three approaches that use different motion con-cepts to improve the identification and separation of precomputed clusters in scatterplots. First, we present two techniques generating real motion effects by the use of flickering and by the use of differ-ent weaving patterns. Furthermore, we present a technique using mimic motion by the use of peripheral drift.
A scatterplot is one of the most popular techniques used for visualizing multidimensional dataset... more A scatterplot is one of the most popular techniques used for visualizing multidimensional datasets. However, if the number of data points is large, occlusion and overdraw problems occur. Thus, it will be difficult to visually differentiate these data points and their clusters. Motion is one of the strongest low-level perceptual cues to draw our visual system’s attention to a certain subset of data. In this paper, we present three approaches that use different motion concepts to improve the identification and separation of precomputed clusters in scatterplots. First, we present two techniques generating real motion effects by the use of flickering and by the use of different weaving patterns. Furthermore, we present a technique using mimic motion by the use of peripheral drift.
The following system description presents our approach to the detection of persuasion techniques ... more The following system description presents our approach to the detection of persuasion techniques in texts and images. The given task has been framed as a multi-label classification problem with the different techniques serving as class labels. The multi-label classification problem is one in which a list of target variables such as our class labels is associated with every input chunk and assumes that a document can simultaneously and independently be assigned to multiple labels or classes. In order to assign class labels to the given memes, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for token and sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps. To incorporate image features in the multi-modal setting, we rely on the pre-trained VGG-16 model architecture.
The following system description presents our approach to the detection of fake news in texts. Th... more The following system description presents our approach to the detection of fake news in texts. The given task has been framed as a multi-class classification problem. The multi-class classification problem is one in which a target variable such as the given class label is associated with every input chunk. In order to assign class labels to the given documents, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps.
Kurzfassung. Im Kontext der Genexpressionsanalyse haben sich parallele Koordinaten (PK) als ein h... more Kurzfassung. Im Kontext der Genexpressionsanalyse haben sich parallele Koordinaten (PK) als ein hilfreiches Werkzeug erwiesen. Ein hochdimensionaler Datensatz kann auf diese Weise in einem zweidimensionalen Datenraum dargestellt werden. Dabei wird die Anzahl der darstellbaren Dimensionen lediglich durch den horizontal verfugbaren Platz begrenzt und ermoglicht ein relativ leichtes Erkennen inharenter Zusammenhange innerhalb eines Kontextes. Neben den offensichtlichen Vorteilen sind jedoch auch die damit verbundenen Beschrankungen zu berucksichtigen. Durch Uberlagerung einzelner Linien kann diese Darstellung relativ schnell uberzeichnet werden und verliert in diesen Bereichen an Informationsgehalt. Daruber hinaus stellt sich die Detektion von Korrelationen uber mehrere Achsen als eine relativ schwierige Aufgabe dar. Um die Frequenz von Kantenzugen entlang der Koordinatenachsen zu erhalten, werden zur graphischen Darstellung Histogramme herangezogen, welche jeweils an den Koordinatenac...
The following system description presents our approach to the estimation of check-worthiness of t... more The following system description presents our approach to the estimation of check-worthiness of text chunks. The given task has been framed as a regression problem. In order predict a numerical value for a chunk we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps.
The information space, where information is generated, stored, exchanged and discussed, is not id... more The information space, where information is generated, stored, exchanged and discussed, is not idyllic but a space where campaigns of disinformation and destabilization are conducted. Such campaigns are subsumed under the terms “hybrid warfare” and “information warfare” (Woolley and Howard, 2017). In order to enable awareness of them, we propose an information state dashboard comprising various components/apps for data collection, analysis and visualization. The aim of the dashboard is to support an analyst in generating a common operational picture of the information space, link it with an operational picture of the physical space and, thus, contribute to overarching situational awareness. The dashboard is work in progress. However, a first prototype with components for exploiting elementary language statistics, keyword and metadata analysis, text classification and network analysis has been implemented. Further components, in particular, for event extraction and sentiment analysis...
2021 International Conference on Military Communication and Information Systems (ICMCIS)
The Internet has long since established itself as an indispensable source of information for both... more The Internet has long since established itself as an indispensable source of information for both organizations and individuals. The lack of social responsibility of many digital platforms, however, offers many incentives for various forms of abuse. Disinformation, propaganda and fake news are just a few examples. Among the actors of information campaigns, we find not only individuals but also state actors with a clear agenda. Often, such information campaigns make use of psychological and rhetorical methods to achieve their goals. The manipulation of information is a major challenge for our democracies. It also presents us with major technical problems to identify and assess risks arising from the dissemination of such information.The following system description presents our approach to the detection of misinformation on social media data, which is twofold. Initially, we subjected the given training data to an exploratory analysis to get an overview of the general structure. Then we framed the given task as a simpler classification problem. In order to distinguish between trusted and untrusted information, using BERT (Bidirectional Encoder Representations from Transformers) as a neural network architecture for sequence classification, we started with a pre-trained model for language representation. In a supervised training step we fine-tuned this model on the given classification task with the provided annotated data.In this paper we would like to discuss both the quality of the training data and the performance of the trained classifier to derive promising directions for future work.
This paper describes the design and implementation of an interactive walk-through of a reconstruc... more This paper describes the design and implementation of an interactive walk-through of a reconstructed German stronghold, the Dillenburg. The application is currently in use at the local museum. Applying technologies and algorithms primarily used for the development of realis-tic 3D computer games, we present a system that can be categorized as a Serious Gaming environment, a term that has recently come into existence. More specifically, it can be called a Cultural Heritage Game. With this pa-per we want to give a programmer’s view on the topic of interactive cultural heritage systems.
Uploads
Papers by Albert Pritzkau