@misc{SeewannVerwiebeBuderetal.2022,
  author    = {Seewann, Lena and Verwiebe, Roland and Buder, Claudia and Fritsch, Nina-Sophie},
  title     = {"Broadcast your gender."},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Wirtschafts- und Sozialwissenschaftliche Reihe},
  number    = {152},
  issn      = {1867-5808},
  doi       = {10.25932/publishup-56628},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566287},
  pages     = {16},
  year      = {2022},
  abstract  = {Social media platforms provide a large array of behavioral data relevant to social scientific research. However, key information such as sociodemographic characteristics of agents are often missing. This paper aims to compare four methods of classifying social attributes from text. Specifically, we are interested in estimating the gender of German social media creators. By using the example of a random sample of 200 YouTube channels, we compare several classification methods, namely (1) a survey among university staff, (2) a name dictionary method with the World Gender Name Dictionary as a reference list, (3) an algorithmic approach using the website gender-api.com, and (4) a Multinomial Na{\"i}ve Bayes (MNB) machine learning technique. These different methods identify gender attributes based on YouTube channel names and descriptions in German but are adaptable to other languages. Our contribution will evaluate the share of identifiable channels, accuracy and meaningfulness of classification, as well as limits and benefits of each approach. We aim to address methodological challenges connected to classifying gender attributes for YouTube channels as well as related to reinforcing stereotypes and ethical implications.},
  language  = {en}
}
@phdthesis{Zali2023,
  author    = {Zali, Zahra},
  title     = {Volcanic tremor analysis based on advanced signal processing concepts including music information retrieval (MIR) strategies},
  doi       = {10.25932/publishup-61086},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-610866},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, 95},
  year      = {2023},
  abstract  = {Volcanoes are one of the Earth's most dynamic zones and responsible for many changes in our planet. Volcano seismology aims to provide an understanding of the physical processes in volcanic systems and anticipate the style and timing of eruptions by analyzing the seismic records. Volcanic tremor signals are usually observed in the seismic records before or during volcanic eruptions. Their analysis contributes to evaluate the evolving volcanic activity and potentially predict eruptions. Years of continuous seismic monitoring now provide useful information for operational eruption forecasting. The continuously growing amount of seismic recordings, however, poses a challenge for analysis, information extraction, and interpretation, to support timely decision making during volcanic crises. Furthermore, the complexity of eruption processes and precursory activities makes the analysis challenging. A challenge in studying seismic signals of volcanic origin is the coexistence of transient signal swarms and long-lasting volcanic tremor signals. Separating transient events from volcanic tremors can, therefore, contribute to improving our understanding of the underlying physical processes. Some similar issues (data reduction, source separation, extraction, and classification) are addressed in the context of music information retrieval (MIR). The signal characteristics of acoustic and seismic recordings comprise a number of similarities. This thesis is going beyond classical signal analysis techniques usually employed in seismology by exploiting similarities of seismic and acoustic signals and building the information retrieval strategy on the expertise developed in the field of MIR. First, inspired by the idea of harmonic-percussive separation (HPS) in musical signal processing, I have developed a method to extract harmonic volcanic tremor signals and to detect transient events from seismic recordings. This provides a clean tremor signal suitable for tremor investigation along with a characteristic function suitable for earthquake detection. Second, using HPS algorithms, I have developed a noise reduction technique for seismic signals. This method is especially useful for denoising ocean bottom seismometers, which are highly contaminated by noise. The advantage of this method compared to other denoising techniques is that it doesn't introduce distortion to the broadband earthquake waveforms, which makes it reliable for different applications in passive seismological analysis. Third, to address the challenge of extracting information from high-dimensional data and investigating the complex eruptive phases, I have developed an advanced machine learning model that results in a comprehensive signal processing scheme for volcanic tremors. Using this method seismic signatures of major eruptive phases can be automatically detected. This helps to provide a chronology of the volcanic system. Also, this model is capable to detect weak precursory volcanic tremors prior to the eruption, which could be used as an indicator of imminent eruptive activity. The extracted patterns of seismicity and their temporal variations finally provide an explanation for the transition mechanism between eruptive phases.},
  language  = {en}
}
@misc{HeckerSteckhanEybenetal.2022,
  author    = {Hecker, Pascal and Steckhan, Nico and Eyben, Florian and Schuller, Bj{\"o}rn Wolfgang and Arnrich, Bert},
  title     = {Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {13},
  doi       = {10.25932/publishup-58101},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581019},
  pages     = {16},
  year      = {2022},
  abstract  = {Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.},
  language  = {en}
}
@phdthesis{Elsaid2022,
  author    = {Elsaid, Mohamed Esameldin Mohamed},
  title     = {Virtual machines live migration cost modeling and prediction},
  doi       = {10.25932/publishup-54001},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-540013},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 107},
  year      = {2022},
  abstract  = {Dynamic resource management is an essential requirement for private and public cloud computing environments. With dynamic resource management, the physical resources assignment to the cloud virtual resources depends on the actual need of the applications or the running services, which enhances the cloud physical resources utilization and reduces the offered services cost. In addition, the virtual resources can be moved across different physical resources in the cloud environment without an obvious impact on the running applications or services production. This means that the availability of the running services and applications in the cloud is independent on the hardware resources including the servers, switches and storage failures. This increases the reliability of using cloud services compared to the classical data-centers environments. In this thesis we briefly discuss the dynamic resource management topic and then deeply focus on live migration as the definition of the compute resource dynamic management. Live migration is a commonly used and an essential feature in cloud and virtual data-centers environments. Cloud computing load balance, power saving and fault tolerance features are all dependent on live migration to optimize the virtual and physical resources usage. As we will discuss in this thesis, live migration shows many benefits to cloud and virtual data-centers environments, however the cost of live migration can not be ignored. Live migration cost includes the migration time, downtime, network overhead, power consumption increases and CPU overhead. IT admins run virtual machines live migrations without an idea about the migration cost. So, resources bottlenecks, higher migration cost and migration failures might happen. The first problem that we discuss in this thesis is how to model the cost of the virtual machines live migration. Secondly, we investigate how to make use of machine learning techniques to help the cloud admins getting an estimation of this cost before initiating the migration for one of multiple virtual machines. Also, we discuss the optimal timing for a specific virtual machine before live migration to another server. Finally, we propose practical solutions that can be used by the cloud admins to be integrated with the cloud administration portals to answer the raised research questions above. Our research methodology to achieve the project objectives is to propose empirical models based on using VMware test-beds with different benchmarks tools. Then we make use of the machine learning techniques to propose a prediction approach for virtual machines live migration cost. Timing optimization for live migration is also proposed in this thesis based on using the cost prediction and data-centers network utilization prediction. Live migration with persistent memory clusters is also discussed at the end of the thesis. The cost prediction and timing optimization techniques proposed in this thesis could be practically integrated with VMware vSphere cluster portal such that the IT admins can now use the cost prediction feature and timing optimization option before proceeding with a virtual machine live migration. Testing results show that our proposed approach for VMs live migration cost prediction shows acceptable results with less than 20\% prediction error and can be easily implemented and integrated with VMware vSphere as an example of a commonly used resource management portal for virtual data-centers and private cloud environments. The results show that using our proposed VMs migration timing optimization technique also could save up to 51\% of migration time of the VMs migration time for memory intensive workloads and up to 27\% of the migration time for network intensive workloads. This timing optimization technique can be useful for network admins to save migration time with utilizing higher network rate and higher probability of success. At the end of this thesis, we discuss the persistent memory technology as a new trend in servers memory technology. Persistent memory modes of operation and configurations are discussed in detail to explain how live migration works between servers with different memory configuration set up. Then, we build a VMware cluster with persistent memory inside server and also with DRAM only servers to show the live migration cost difference between the VMs with DRAM only versus the VMs with persistent memory inside.},
  language  = {en}
}
@phdthesis{Smirnov2023,
  author    = {Smirnov, Artem},
  title     = {Understanding the dynamics of the near-earth space environment utilizing long-term satellite observations},
  doi       = {10.25932/publishup-61371},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613711},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxxvi, 286},
  year      = {2023},
  abstract  = {The near-Earth space environment is a highly complex system comprised of several regions and particle populations hazardous to satellite operations. The trapped particles in the radiation belts and ring current can cause significant damage to satellites during space weather events, due to deep dielectric and surface charging. Closer to Earth is another important region, the ionosphere, which delays the propagation of radio signals and can adversely affect navigation and positioning. In response to fluctuations in solar and geomagnetic activity, both the inner-magnetospheric and ionospheric populations can undergo drastic and sudden changes within minutes to hours, which creates a challenge for predicting their behavior. Given the increasing reliance of our society on satellite technology, improving our understanding and modeling of these populations is a matter of paramount importance. In recent years, numerous spacecraft have been launched to study the dynamics of particle populations in the near-Earth space, transforming it into a data-rich environment. To extract valuable insights from the abundance of available observations, it is crucial to employ advanced modeling techniques, and machine learning methods are among the most powerful approaches available. This dissertation employs long-term satellite observations to analyze the processes that drive particle dynamics, and builds interdisciplinary links between space physics and machine learning by developing new state-of-the-art models of the inner-magnetospheric and ionospheric particle dynamics. The first aim of this thesis is to investigate the behavior of electrons in Earth's radiation belts and ring current. Using ~18 years of electron flux observations from the Global Positioning System (GPS), we developed the first machine learning model of hundreds-of-keV electron flux at Medium Earth Orbit (MEO) that is driven solely by solar wind and geomagnetic indices and does not require auxiliary flux measurements as inputs. We then proceeded to analyze the directional distributions of electrons, and for the first time, used Fourier sine series to fit electron pitch angle distributions (PADs) in Earth's inner magnetosphere. We performed a superposed epoch analysis of 129 geomagnetic storms during the Van Allen Probes era and demonstrated that electron PADs have a strong energy-dependent response to geomagnetic activity. Additionally, we showed that the solar wind dynamic pressure could be used as a good predictor of the PAD dynamics. Using the observed dependencies, we created the first PAD model with a continuous dependence on L, magnetic local time (MLT) and activity, and developed two techniques to reconstruct near-equatorial electron flux observations from low-PA data using this model. The second objective of this thesis is to develop a novel model of the topside ionosphere. To achieve this goal, we collected observations from five of the most widely used ionospheric missions and intercalibrated these data sets. This allowed us to use these data jointly for model development, validation, and comparison with other existing empirical models. We demonstrated, for the first time, that ion density observations by Swarm Langmuir Probes exhibit overestimation (up to ~40-50\%) at low and mid-latitudes on the night side, and suggested that the influence of light ions could be a potential cause of this overestimation. To develop the topside model, we used 19 years of radio occultation (RO) electron density profiles, which were fitted with a Chapman function with a linear dependence of scale height on altitude. This approximation yields 4 parameters, namely the peak density and height of the F2-layer and the slope and intercept of the linear scale height trend, which were modeled using feedforward neural networks (NNs). The model was extensively validated against both RO and in-situ observations and was found to outperform the International Reference Ionosphere (IRI) model by up to an order of magnitude. Our analysis showed that the most substantial deviations of the IRI model from the data occur at altitudes of 100-200 km above the F2-layer peak. The developed NN-based ionospheric model reproduces the effects of various physical mechanisms observed in the topside ionosphere and provides highly accurate electron density predictions. This dissertation provides an extensive study of geospace dynamics, and the main results of this work contribute to the improvement of models of plasma populations in the near-Earth space environment.},
  language  = {en}
}
@phdthesis{Seleem2023,
  author    = {Seleem, Omar},
  title     = {Towards urban pluvial flood mapping using data-driven models},
  doi       = {10.25932/publishup-59813},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598137},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 95},
  year      = {2023},
  abstract  = {Casualties and damages from urban pluvial flooding are increasing. Triggered by short, localized, and intensive rainfall events, urban pluvial floods can occur anywhere, even in areas without a history of flooding. Urban pluvial floods have relatively small temporal and spatial scales. Although cumulative losses from urban pluvial floods are comparable, most flood risk management and mitigation strategies focus on fluvial and coastal flooding. Numerical-physical-hydrodynamic models are considered the best tool to represent the complex nature of urban pluvial floods; however, they are computationally expensive and time-consuming. These sophisticated models make large-scale analysis and operational forecasting prohibitive. Therefore, it is crucial to evaluate and benchmark the performance of other alternative methods. The findings of this cumulative thesis are represented in three research articles. The first study evaluates two topographic-based methods to map urban pluvial flooding, fill-spill-merge (FSM) and topographic wetness index (TWI), by comparing them against a sophisticated hydrodynamic model. The FSM method identifies flood-prone areas within topographic depressions while the TWI method employs maximum likelihood estimation to calibrate a TWI threshold (τ) based on inundation maps from the 2D hydrodynamic model. The results point out that the FSM method outperforms the TWI method. The study highlights then the advantage and limitations of both methods. Data-driven models provide a promising alternative to computationally expensive hydrodynamic models. However, the literature lacks benchmarking studies to evaluate the different models' performance, advantages and limitations. Model transferability in space is a crucial problem. Most studies focus on river flooding, likely due to the relative availability of flow and rain gauge records for training and validation. Furthermore, they consider these models as black boxes. The second study uses a flood inventory for the city of Berlin and 11 predictive features which potentially indicate an increased pluvial flooding hazard to map urban pluvial flood susceptibility using a convolutional neural network (CNN), an artificial neural network (ANN) and the benchmarking machine learning models random forest (RF) and support vector machine (SVM). I investigate the influence of spatial resolution on the implemented models, the models' transferability in space and the importance of the predictive features. The results show that all models perform well and the RF models are superior to the other models within and outside the training domain. The models developed using fine spatial resolution (2 and 5 m) could better identify flood-prone areas. Finally, the results point out that aspect is the most important predictive feature for the CNN models, and altitude is for the other models. While flood susceptibility maps identify flood-prone areas, they do not represent flood variables such as velocity and depth which are necessary for effective flood risk management. To address this, the third study investigates data-driven models' transferability to predict urban pluvial floodwater depth and the models' ability to enhance their predictions using transfer learning techniques. It compares the performance of RF (the best-performing model in the previous study) and CNN models using 12 predictive features and output from a hydrodynamic model. The findings in the third study suggest that while CNN models tend to generalise and smooth the target function on the training dataset, RF models suffer from overfitting. Hence, RF models are superior for predictions inside the training domains but fail outside them while CNN models could control the relative loss in performance outside the training domains. Finally, the CNN models benefit more from transfer learning techniques than RF models, boosting their performance outside training domains. In conclusion, this thesis has evaluated both topographic-based methods and data-driven models to map urban pluvial flooding. However, further studies are crucial to have methods that completely overcome the limitation of 2D hydrodynamic models.},
  language  = {en}
}
@phdthesis{Sidarenka2019,
  author    = {Sidarenka, Uladzimir},
  title     = {Sentiment analysis of German Twitter},
  doi       = {10.25932/publishup-43742},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-437422},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 217},
  year      = {2019},
  abstract  = {The immense popularity of online communication services in the last decade has not only upended our lives (with news spreading like wildfire on the Web, presidents announcing their decisions on Twitter, and the outcome of political elections being determined on Facebook) but also dramatically increased the amount of data exchanged on these platforms. Therefore, if we wish to understand the needs of modern society better and want to protect it from new threats, we urgently need more robust, higher-quality natural language processing (NLP) applications that can recognize such necessities and menaces automatically, by analyzing uncensored texts. Unfortunately, most NLP programs today have been created for standard language, as we know it from newspapers, or, in the best case, adapted to the specifics of English social media. This thesis reduces the existing deficit by entering the new frontier of German online communication and addressing one of its most prolific forms—users' conversations on Twitter. In particular, it explores the ways and means by how people express their opinions on this service, examines current approaches to automatic mining of these feelings, and proposes novel methods, which outperform state-of-the-art techniques. For this purpose, I introduce a new corpus of German tweets that have been manually annotated with sentiments, their targets and holders, as well as lexical polarity items and their contextual modifiers. Using these data, I explore four major areas of sentiment research: (i) generation of sentiment lexicons, (ii) fine-grained opinion mining, (iii) message-level polarity classification, and (iv) discourse-aware sentiment analysis. In the first task, I compare three popular groups of lexicon generation methods: dictionary-, corpus-, and word-embedding-based ones, finding that dictionary-based systems generally yield better polarity lists than the last two groups. Apart from this, I propose a linear projection algorithm, whose results surpass many existing automatically-generated lexicons. Afterwords, in the second task, I examine two common approaches to automatic prediction of sentiment spans, their sources, and targets: conditional random fields (CRFs) and recurrent neural networks, obtaining higher scores with the former model and improving these results even further by redefining the structure of CRF graphs. When dealing with message-level polarity classification, I juxtapose three major sentiment paradigms: lexicon-, machine-learning-, and deep-learning-based systems, and try to unite the first and last of these method groups by introducing a bidirectional neural network with lexicon-based attention. Finally, in order to make the new classifier aware of microblogs' discourse structure, I let it separately analyze the elementary discourse units of each tweet and infer the overall polarity of a message from the scores of its EDUs with the help of two new approaches: latent-marginalized CRFs and Recursive Dirichlet Process.},
  language  = {en}
}
@phdthesis{Lazaridou2021,
  author    = {Lazaridou, Konstantina},
  title     = {Revealing hidden patterns in political news and social media with machine learning},
  doi       = {10.25932/publishup-50273},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-502734},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 140},
  year      = {2021},
  abstract  = {As part of our everyday life we consume breaking news and interpret it based on our own viewpoints and beliefs. We have easy access to online social networking platforms and news media websites, where we inform ourselves about current affairs and often post about our own views, such as in news comments or social media posts. The media ecosystem enables opinions and facts to travel from news sources to news readers, from news article commenters to other readers, from social network users to their followers, etc. The views of the world many of us have depend on the information we receive via online news and social media. Hence, it is essential to maintain accurate, reliable and objective online content to ensure democracy and verity on the Web. To this end, we contribute to a trustworthy media ecosystem by analyzing news and social media in the context of politics to ensure that media serves the public interest. In this thesis, we use text mining, natural language processing and machine learning techniques to reveal underlying patterns in political news articles and political discourse in social networks. Mainstream news sources typically cover a great amount of the same news stories every day, but they often place them in a different context or report them from different perspectives. In this thesis, we are interested in how distinct and predictable newspaper journalists are, in the way they report the news, as a means to understand and identify their different political beliefs. To this end, we propose two models that classify text from news articles to their respective original news source, i.e., reported speech and also news comments. Our goal is to capture systematic quoting and commenting patterns by journalists and news commenters respectively, which can lead us to the newspaper where the quotes and comments are originally published. Predicting news sources can help us understand the potential subjective nature behind news storytelling and the magnitude of this phenomenon. Revealing this hidden knowledge can restore our trust in media by advancing transparency and diversity in the news. Media bias can be expressed in various subtle ways in the text and it is often challenging to identify these bias manifestations correctly, even for humans. However, media experts, e.g., journalists, are a powerful resource that can help us overcome the vague definition of political media bias and they can also assist automatic learners to find the hidden bias in the text. Due to the enormous technological advances in artificial intelligence, we hypothesize that identifying political bias in the news could be achieved through the combination of sophisticated deep learning modelsxi and domain expertise. Therefore, our second contribution is a high-quality and reliable news dataset annotated by journalists for political bias and a state-of-the-art solution for this task based on curriculum learning. Our aim is to discover whether domain expertise is necessary for this task and to provide an automatic solution for this traditionally manually-solved problem. User generated content is fundamentally different from news articles, e.g., messages are shorter, they are often personal and opinionated, they refer to specific topics and persons, etc. Regarding political and socio-economic news, individuals in online communities make use of social networks to keep their peers up-to-date and to share their own views on ongoing affairs. We believe that social media is also an as powerful instrument for information flow as the news sources are, and we use its unique characteristic of rapid news coverage for two applications. We analyze Twitter messages and debate transcripts during live political presidential debates to automatically predict the topics that Twitter users discuss. Our goal is to discover the favoured topics in online communities on the dates of political events as a way to understand the political subjects of public interest. With the up-to-dateness of microblogs, an additional opportunity emerges, namely to use social media posts and leverage the real-time verity about discussed individuals to find their locations. That is, given a person of interest that is mentioned in online discussions, we use the wisdom of the crowd to automatically track her physical locations over time. We evaluate our approach in the context of politics, i.e., we predict the locations of US politicians as a proof of concept for important use cases, such as to track people that are national risks, e.g., warlords and wanted criminals.},
  language  = {en}
}
@phdthesis{Mientus2023,
  author    = {Mientus, Lukas},
  title     = {Reflexion und Reflexivit{\"a}t},
  doi       = {10.25932/publishup-61000},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-610003},
  school      = {Universit{\"a}t Potsdam},
  pages     = {121},
  year      = {2023},
  abstract  = {Reflexion gilt in der Lehrkr{\"a}ftebildung als eine Schl{\"u}sselkategorie der professionellen Entwicklung. Entsprechend wird auf vielf{\"a}ltige Weise die Qualit{\"a}t reflexionsbezogener Kompetenzen untersucht. Eine Herausforderung hierbei kann in der Annahme bestehen, von der Analyse schriftlicher Reflexionen unmittelbar auf die Reflexivit{\"a}t einer Person zu schließen, da Reflexion stets kontextspezifisch als Abbild reflexionsbezogener Argumentationsprozesse angesehen werden sollte und reflexionsbezogenen Dispositionen unterliegt. Auch kann die Qualit{\"a}t einer Reflexion auf mehreren Dimensionen bewertet werden, ohne quantifizierbare, absolute Aussagen treffen zu k{\"o}nnen. Daher wurden im Rahmen einer Physik-Videovignette N = 134 schriftliche Fremdreflexionen verfasst und kontextspezifische reflexionsbezogene Dispositionen erhoben. Expert*innen erstellten theoriegeleitet Qualit{\"a}tsbewertungen zur Breite, Tiefe, Koh{\"a}renz und Spezifit{\"a}t eines jeden Reflexionstextes. Unter Verwendung computerbasierter Klassifikations- und Analyseverfahren wurden weitere Textmerkmale erhoben. Mittels explorativer Faktorenanalyse konnten die Faktoren Qualit{\"a}t, Quantit{\"a}t und Deskriptivit{\"a}t gefunden werden. Da alle konventionell eingesch{\"a}tzten Qualit{\"a}tsbewertungen durch einen Faktor repr{\"a}sentiert wurden, konnte ein maximales Qualit{\"a}tskorrelat kalkuliert werden, zu welchem jede schriftliche Fremdreflexion im Rahmen der vorliegenden Vignette eine computerbasiert bestimmbare Distanz aufweist. Diese Distanz zum maximalen Qualit{\"a}tskorrelat konnte validiert werden und kann die Qualit{\"a}t der schriftlichen Reflexionen unabh{\"a}ngig von menschlichen Ressourcen quantifiziert repr{\"a}sentieren. Abschließend konnte identifiziert werden, dass ausgew{\"a}hlte Dispositionen in unterschiedlichem Maße mit der Reflexionsqualit{\"a}t zusammenh{\"a}ngen. So konnten beispielsweise bezogen auf das Physik-Fachwissen minimale Zusammenh{\"a}nge identifiziert werden, wohingegen Werthaltung sowie wahrgenommene Unterrichtsqualit{\"a}t eng mit der Qualit{\"a}t einer schriftlichen Reflexion in Verbindung stehen k{\"o}nnen. Es wird geschlussfolgert, dass reflexionsbezogene Dispositionen moderierenden Einfluss auf Reflexionen nehmen k{\"o}nnen. Es wird empfohlen bei der Erhebung von Reflexion mit dem Ziel der Kompetenzmessung ausgew{\"a}hlte Dispositionen mit zu erheben. Weiter verdeutlicht diese Arbeit die M{\"o}glichkeit, aussagekr{\"a}ftige Quantifizierungen auch in der Analyse komplexer Konstrukte vorzunehmen. Durch computerbasierte Qualit{\"a}tsabsch{\"a}tzungen k{\"o}nnen objektive und individuelle Analysen und differenzierteres automatisiertes Feedback erm{\"o}glicht werden.},
  language  = {de}
}
@misc{KibrikKhudyakovaDobrovetal.2016,
  author    = {Kibrik, Andrej A. and Khudyakova, Mariya V. and Dobrov, Grigory B. and Linnik, Anastasia and Zalmanov, Dmitrij A.},
  title     = {Referential Choice},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100313},
  pages     = {21},
  year      = {2016},
  abstract  = {We report a study of referential choice in discourse production, understood as the choice between various types of referential devices, such as pronouns and full noun phrases. Our goal is to predict referential choice, and to explore to what extent such prediction is possible. Our approach to referential choice includes a cognitively informed theoretical component, corpus analysis, machine learning methods and experimentation with human participants. Machine learning algorithms make use of 25 factors, including referent's properties (such as animacy and protagonism), the distance between a referential expression and its antecedent, the antecedent's syntactic role, and so on. Having found the predictions of our algorithm to coincide with the original almost 90\% of the time, we hypothesized that fully accurate prediction is not possible because, in many situations, more than one referential option is available. This hypothesis was supported by an experimental study, in which participants answered questions about either the original text in the corpus, or about a text modified in accordance with the algorithm's prediction. Proportions of correct answers to these questions, as well as participants' rating of the questions' difficulty, suggested that divergences between the algorithm's prediction and the original referential device in the corpus occur overwhelmingly in situations where the referential choice is not categorical.},
  language  = {en}
}