@article{RischKrestel2020,
  author    = {Risch, Julian and Krestel, Ralf},
  title     = {Toxic comment detection in online discussions},
  series = {Deep learning-based approaches for sentiment analysis},
  journal   = {Deep learning-based approaches for sentiment analysis},
  editor    = {Agarwal, Basant and Nayak, Richi and Mittal, Namita and Patnaik, Srikanta},
  publisher = {Springer},
  address   = {Singapore},
  isbn      = {978-981-15-1216-2},
  issn      = {2524-7565},
  doi       = {10.1007/978-981-15-1216-2_4},
  pages     = {85 -- 109},
  year      = {2020},
  abstract  = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. In contrast to other online posts, news discussions are related to particular news articles, comments refer to each other, and individual conversations emerge. However, the misuse by spammers, haters, and trolls makes costly content moderation necessary. Sentiment analysis can not only support moderation but also help to understand the dynamics of online discussions. A subtask of content moderation is the identification of toxic comments. To this end, we describe the concept of toxicity and characterize its subclasses. Further, we present various deep learning approaches, including datasets and architectures, tailored to sentiment analysis in online discussions. One way to make these approaches more comprehensible and trustworthy is fine-grained instead of binary comment classification. On the downside, more classes require more training data. Therefore, we propose to augment training data by using transfer learning. We discuss real-world applications, such as semi-automated comment moderation and troll detection. Finally, we outline future challenges and current limitations in light of most recent research publications.},
  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}
}
@misc{SeleemAyzelCostaTomazdeSouzaetal.2022,
  author    = {Seleem, Omar and Ayzel, Georgy and Costa Tomaz de Souza, Arthur and Bronstert, Axel and Heistermann, Maik},
  title     = {Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1297},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-57680},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-576806},
  pages     = {1640 -- 1662},
  year      = {2022},
  abstract  = {Identifying urban pluvial flood-prone areas is necessary but the application of two-dimensional hydrodynamic models is limited to small areas. Data-driven models have been showing their ability to map flood susceptibility but their application in urban pluvial flooding is still rare. A flood inventory (4333 flooded locations) and 11 factors which potentially indicate an increased hazard for pluvial flooding were used to implement convolutional neural network (CNN), artificial neural network (ANN), random forest (RF) and support vector machine (SVM) to: (1) Map flood susceptibility in Berlin at 30, 10, 5, and 2 m spatial resolutions. (2) Evaluate the trained models' transferability in space. (3) Estimate the most useful factors for flood susceptibility mapping. The models' performance was validated using the Kappa, and the area under the receiver operating characteristic curve (AUC). The results indicated that all models perform very well (minimum AUC = 0.87 for the testing dataset). The RF models outperformed all other models at all spatial resolutions and the RF model at 2 m spatial resolution was superior for the present flood inventory and predictor variables. The majority of the models had a moderate performance for predictions outside the training area based on Kappa evaluation (minimum AUC = 0.8). Aspect and altitude were the most influencing factors on the image-based and point-based models respectively. Data-driven models can be a reliable tool for urban pluvial flood susceptibility mapping wherever a reliable flood inventory is available.},
  language  = {en}
}
@article{Stober2017,
  author    = {Stober, Sebastian},
  title     = {Toward Studying Music Cognition with Information Retrieval Techniques: Lessons Learned from the OpenMIIR Initiative},
  series = {Frontiers in psychology},
  volume    = {8},
  journal   = {Frontiers in psychology},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1664-1078},
  doi       = {10.3389/fpsyg.2017.01255},
  pages     = {17},
  year      = {2017},
  abstract  = {As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition-such as listening to or imagining music pieces. This is a highly interdisciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings ofmusic perception and imagination have beenmade publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.},
  language  = {en}
}
@article{Stober2017,
  author    = {Stober, Sebastian},
  title     = {Toward Studying Music Cognition with Information Retrieval Techniques},
  series = {Frontiers in psychology},
  volume    = {8},
  journal   = {Frontiers in psychology},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1664-1078},
  doi       = {10.3389/fpsyg.2017.01255},
  year      = {2017},
  abstract  = {As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition-such as listening to or imagining music pieces. This is a highly inter-disciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings of music perception and imagination have been made publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.},
  language  = {en}
}
@misc{Stober2017,
  author    = {Stober, Sebastian},
  title     = {Toward Studying Music Cognition with Information Retrieval Techniques},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-402762},
  pages     = {17},
  year      = {2017},
  abstract  = {As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition-such as listening to or imagining music pieces. This is a highly inter-disciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings of music perception and imagination have been made publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.},
  language  = {en}
}
@phdthesis{Pfrang2023,
  author    = {Pfrang, Konstantin Johannes},
  title     = {Search for light primordial black holes with VERITAS using gamma γ-ray and optical observations},
  doi       = {10.25932/publishup-58726},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-587266},
  school      = {Universit{\"a}t Potsdam},
  pages     = {139},
  year      = {2023},
  abstract  = {The Very Energetic Radiation Imaging Telescope Array System (VERITAS) is an array of four imaging atmospheric Cherenkov telescopes (IACTs). VERITAS is sensitive to very-high-energy gamma-rays in the range of 100 GeV to >30 TeV. Hypothesized primordial black holes (PBHs) are attractive targets for IACTs. If they exist, their potential cosmological impact reaches beyond the candidacy for constituents of dark matter. The sublunar mass window is the largest unconstrained range of PBH masses. This thesis aims to develop novel concepts searching for light PBHs with VERITAS. PBHs below the sublunar window lose mass due to Hawking radiation. They would evaporate at the end of their lifetime, leading to a short burst of gamma-rays. If PBHs formed at about 10^15 g, the evaporation would occur nowadays. Detecting these signals might not only confirm the existence of PBHs but also prove the theory of Hawking radiation. This thesis probes archival VERITAS data recorded between 2012 and 2021 for possible PBH signals. This work presents a new automatic approach to assess the quality of the VERITAS data. The array-trigger rate and far infrared temperature are well suited to identify periods with poor data quality. These are masked by time cuts to obtain a consistent and clean dataset which contains about 4222 hours. The PBH evaporations could occur at any location in the field of view or time within this data. Only a blind search can be performed to identify these short signals. This thesis implements a data-driven deep learning based method to search for short transient signals with VERITAS. It does not depend on the modelling of the effective area and radial acceptance. This work presents the first application of this method to actual observational IACT data. This thesis develops new concepts dealing with the specifics of the data and the transient detection method. These are reflected in the developed data preparation pipeline and search strategies. After correction for trial factors, no candidate PBH evaporation is found in the data. Thus, new constraints of the local rate of PBH evaporations are derived. At the 99\% confidence limit it is below <1.07 * 10^5 pc^-3 yr^-1. This constraint with the new, independent analysis approach is in the range of existing limits for the evaporation rate. This thesis also investigates an alternative novel approach to searching for PBHs with IACTs. Above the sublunar window, the PBH abundance is constrained by optical microlensing studies. The sampling speed, which is of order of minutes to hours for traditional optical telescopes, is a limiting factor in expanding the limits to lower masses. IACTs are also powerful instruments for fast transient optical astronomy with up to O(ns) sampling. This thesis investigates whether IACTs might constrain the sublunar window with optical microlensing observations. This study confirms that, in principle, the fast sampling speed might allow extending microlensing searches into the sublunar mass window. However, the limiting factor for IACTs is the modest sensitivity to detect changes in optical fluxes. This thesis presents the expected rate of detectable events for VERITAS as well as prospects of possible future next-generation IACTs. For VERITAS, the rate of detectable microlensing events in the sublunar range is ~10^-6 per year of observation time. The future prospects for a 100 times more sensitive instrument are at ~0.05 events per year.},
  language  = {en}
}
@article{WilkschAbramova2023,
  author    = {Wilksch, Moritz and Abramova, Olga},
  title     = {PyFin-sentiment},
  series = {International journal of information management data insights},
  volume    = {3},
  journal   = {International journal of information management data insights},
  number    = {1},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {2667-0968},
  doi       = {10.1016/j.jjimei.2023.100171},
  pages     = {10},
  year      = {2023},
  abstract  = {Responding to the poor performance of generic automated sentiment analysis solutions on domain-specific texts, we collect a dataset of 10,000 tweets discussing the topics of finance and investing. We manually assign each tweet its market sentiment, i.e., the investor's anticipation of a stock's future return. Using this data, we show that all existing sentiment models trained on adjacent domains struggle with accurate market sentiment analysis due to the task's specialized vocabulary. Consequently, we design, train, and deploy our own sentiment model. It outperforms all previous models (VADER, NTUSD-Fin, FinBERT, TwitterRoBERTa) when evaluated on Twitter posts. On posts from a different platform, our model performs on par with BERT-based large language models. We achieve this result at a fraction of the training and inference costs due to the model's simple design. We publish the artifact as a python library to facilitate its use by future researchers and practitioners.},
  language  = {en}
}
@misc{BridwellCavanaghCollinsetal.2018,
  author    = {Bridwell, David A. and Cavanagh, James F. and Collins, Anne G. E. and Nunez, Michael D. and Srinivasan, Ramesh and Stober, Sebastian and Calhoun, Vince D.},
  title     = {Moving Beyond ERP Components},
  series = {Frontiers in human neuroscienc},
  volume    = {12},
  journal   = {Frontiers in human neuroscienc},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1662-5161},
  doi       = {10.3389/fnhum.2018.00106},
  pages     = {17},
  year      = {2018},
  abstract  = {Relationships between neuroimaging measures and behavior provide important clues about brain function and cognition in healthy and clinical populations. While electroencephalography (EEG) provides a portable, low cost measure of brain dynamics, it has been somewhat underrepresented in the emerging field of model-based inference. We seek to address this gap in this article by highlighting the utility of linking EEG and behavior, with an emphasis on approaches for EEG analysis that move beyond focusing on peaks or "components" derived from averaging EEG responses across trials and subjects (generating the event-related potential, ERP). First, we review methods for deriving features from EEG in order to enhance the signal within single-trials. These methods include filtering based on user-defined features (i.e., frequency decomposition, time-frequency decomposition), filtering based on data-driven properties (i.e., blind source separation, BSS), and generating more abstract representations of data (e.g., using deep learning). We then review cognitive models which extract latent variables from experimental tasks, including the drift diffusion model (DDM) and reinforcement learning (RL) approaches. Next, we discuss ways to access associations among these measures, including statistical models, data-driven joint models and cognitive joint modeling using hierarchical Bayesian models (HBMs). We think that these methodological tools are likely to contribute to theoretical advancements, and will help inform our understandings of brain dynamics that contribute to moment-to-moment cognitive function.},
  language  = {en}
}
@misc{BridwellCavanaghCollinsetal.2018,
  author    = {Bridwell, David A. and Cavanagh, James F. and Collins, Anne G. E. and Nunez, Michael D. and Srinivasan, Ramesh and Stober, Sebastian and Calhoun, Vince D.},
  title     = {Moving beyond ERP components},
  series = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe},
  number    = {656},
  issn      = {1866-8364},
  doi       = {10.25932/publishup-45966},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-459667},
  pages     = {19},
  year      = {2018},
  abstract  = {Relationships between neuroimaging measures and behavior provide important clues about brain function and cognition in healthy and clinical populations. While electroencephalography (EEG) provides a portable, low cost measure of brain dynamics, it has been somewhat underrepresented in the emerging field of model-based inference. We seek to address this gap in this article by highlighting the utility of linking EEG and behavior, with an emphasis on approaches for EEG analysis that move beyond focusing on peaks or "components" derived from averaging EEG responses across trials and subjects (generating the event-related potential, ERP). First, we review methods for deriving features from EEG in order to enhance the signal within single-trials. These methods include filtering based on user-defined features (i.e., frequency decomposition, time-frequency decomposition), filtering based on data-driven properties (i.e., blind source separation, BSS), and generating more abstract representations of data (e.g., using deep learning). We then review cognitive models which extract latent variables from experimental tasks, including the drift diffusion model (DDM) and reinforcement learning (RL) approaches. Next, we discuss ways to access associations among these measures, including statistical models, data-driven joint models and cognitive joint modeling using hierarchical Bayesian models (HBMs). We think that these methodological tools are likely to contribute to theoretical advancements, and will help inform our understandings of brain dynamics that contribute to moment-to-moment cognitive function.},
  language  = {en}
}