@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} } @article{WulffMientusNowaketal.2023, author = {Wulff, Peter and Mientus, Lukas and Nowak, Anna and Borowski, Andreas}, title = {KI-basierte Auswertung von schriftlichen Unterrichtsreflexionen im Fach Physik und automatisierte R{\"u}ckmeldung}, series = {PSI-Potsdam: Ergebnisbericht zu den Aktivit{\"a}ten im Rahmen der Qualit{\"a}tsoffensive Lehrerbildung (2019-2023) (Potsdamer Beitr{\"a}ge zur Lehrerbildung und Bildungsforschung ; 3)}, journal = {PSI-Potsdam: Ergebnisbericht zu den Aktivit{\"a}ten im Rahmen der Qualit{\"a}tsoffensive Lehrerbildung (2019-2023) (Potsdamer Beitr{\"a}ge zur Lehrerbildung und Bildungsforschung ; 3)}, number = {3}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-568-2}, issn = {2626-3556}, doi = {10.25932/publishup-61636}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616363}, pages = {103 -- 115}, year = {2023}, abstract = {F{\"u}r die Entwicklung professioneller Handlungskompetenzen angehender Lehrkr{\"a}fte stellt die Unterrichtsreflexion ein wichtiges Instrument dar, um Theoriewissen und Praxiserfahrungen in Beziehung zu setzen. Die Auswertung von Unterrichtsreflexionen und eine entsprechende R{\"u}ckmeldung stellt Forschende und Dozierende allerdings vor praktische wie theoretische Herausforderungen. Im Kontext der Forschung zu K{\"u}nstlicher Intelligenz (KI) entwickelte Methoden bieten hier neue Potenziale. Der Beitrag stellt {\"u}berblicksartig zwei Teilstudien vor, die mit Hilfe von KI-Methoden wie dem maschinellen Lernen untersuchen, inwieweit eine Auswertung von Unterrichtsreflexionen angehender Physiklehrkr{\"a}fte auf Basis eines theoretisch abgeleiteten Reflexionsmodells und die automatisierte R{\"u}ckmeldung hierzu m{\"o}glich sind. Dabei wurden unterschiedliche Ans{\"a}tze des maschinellen Lernens verwendet, um modellbasierte Klassifikation und Exploration von Themen in Unterrichtsreflexionen umzusetzen. Die Genauigkeit der Ergebnisse wurde vor allem durch sog. Große Sprachmodelle gesteigert, die auch den Transfer auf andere Standorte und F{\"a}cher erm{\"o}glichen. F{\"u}r die fachdidaktische Forschung bedeuten sie jedoch wiederum neue Herausforderungen, wie etwa systematische Verzerrungen und Intransparenz von Entscheidungen. Dennoch empfehlen wir, die Potenziale der KI-basierten Methoden gr{\"u}ndlicher zu erforschen und konsequent in der Praxis (etwa in Form von Webanwendungen) zu implementieren.}, language = {de} } @article{BaumgartBoosEckstein2023, author = {Baumgart, Lene and Boos, Pauline and Eckstein, Bernd}, title = {Datafication and algorithmic contingency}, series = {Work organisation, labour \& globalisation}, volume = {17}, journal = {Work organisation, labour \& globalisation}, number = {1}, publisher = {Pluto Journals}, address = {London}, issn = {1745-641X}, doi = {10.13169/workorgalaboglob.17.1.0061}, pages = {61 -- 73}, year = {2023}, abstract = {In the context of persistent images of self-perpetuated technologies, we discuss the interplay of digital technologies and organisational dynamics against the backdrop of systems theory. Building on the case of an international corporation that, during an agile reorganisation, introduced an AI-based personnel management platform, we show how technical systems produce a form of algorithmic contingency that subsequently leads to the emergence of formal and informal interaction systems. Using the concept of datafication, we explain how these interactions are barriers to the self-perpetuation of data-based decision-making, making it possible to take into consideration further decision factors and complementing the output of the platform. The research was carried out within the scope of the research project 'Organisational Implications of Digitalisation: The Development of (Post-)Bureaucratic Organisational Structures in the Context of Digital Transformation' funded by the German Research Foundation (DFG).}, language = {en} } @article{KappattanavarHeckerMoontahaetal.2023, author = {Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Moontaha, Sidratul and Steckhan, Nico and Arnrich, Bert}, title = {Food choices after cognitive load}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23146597}, pages = {22}, year = {2023}, abstract = {Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12\% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75\% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.}, language = {en} } @article{HollensteinTrondlePlomeckaetal.2023, author = {Hollenstein, Nora and Trondle, Marius and Plomecka, Martyna and Kiegeland, Samuel and Ozyurt, Yilmazcan and J{\"a}ger, Lena Ann and Langer, Nicolas}, title = {The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data}, series = {Frontiers in psychology}, volume = {13}, journal = {Frontiers in psychology}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {1664-1078}, doi = {10.3389/fpsyg.2022.1028824}, pages = {20}, year = {2023}, abstract = {We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: .}, language = {en} } @article{AndresBruttelFriedrichsen2022, author = {Andres, Maximilian and Bruttel, Lisa and Friedrichsen, Jana}, title = {How communication makes the difference between a cartel and tacit collusion}, series = {European economic review}, volume = {152}, journal = {European economic review}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0014-2921}, doi = {10.1016/j.euroecorev.2022.104331}, pages = {1 -- 18}, year = {2022}, abstract = {This paper sheds new light on the role of communication for cartel formation. Using machine learning to evaluate free-form chat communication among firms in a laboratory experiment, we identify typical communication patterns for both explicit cartel formation and indirect attempts to collude tacitly. We document that firms are less likely to communicate explicitly about price fixing and more likely to use indirect messages when sanctioning institutions are present. This effect of sanctions on communication reinforces the direct cartel-deterring effect of sanctions as collusion is more difficult to reach and sustain without an explicit agreement. Indirect messages have no, or even a negative, effect on prices.}, language = {en} } @article{GhafarianWielandLuettschwageretal.2022, author = {Ghafarian, Fatemeh and Wieland, Ralf and L{\"u}ttschwager, Dietmar and Nendel, Claas}, title = {Application of extreme gradient boosting and Shapley Additive explanations to predict temperature regimes inside forests from standard open-field meteorological data}, series = {Environmental modelling \& software with environment data news}, volume = {156}, journal = {Environmental modelling \& software with environment data news}, publisher = {Elsevier}, address = {Oxford}, issn = {1364-8152}, doi = {10.1016/j.envsoft.2022.105466}, pages = {11}, year = {2022}, abstract = {Forest microclimate can buffer biotic responses to summer heat waves, which are expected to become more extreme under climate warming. Prediction of forest microclimate is limited because meteorological observation standards seldom include situations inside forests. We use eXtreme Gradient Boosting - a Machine Learning technique - to predict the microclimate of forest sites in Brandenburg, Germany, using seasonal data comprising weather features. The analysis was amended by applying a SHapley Additive explanation to show the interaction effect of variables and individualised feature attributions. We evaluate model performance in comparison to artificial neural networks, random forest, support vector machine, and multi-linear regression. After implementing a feature selection, an ensemble approach was applied to combine individual models for each forest and improve robustness over a given single prediction model. The resulting model can be applied to translate climate change scenarios into temperatures inside forests to assess temperature-related ecosystem services provided by forests.}, language = {en} } @article{SeewannVerwiebeBuderetal.2022, author = {Seewann, Lena and Verwiebe, Roland and Buder, Claudia and Fritsch, Nina-Sophie}, title = {"Broadcast your gender."}, series = {Frontiers in Big Data}, journal = {Frontiers in Big Data}, number = {5}, publisher = {Frontiers}, address = {Lausanne, Schweiz}, issn = {2624-909X}, doi = {10.3389/fdata.2022.908636}, 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} } @article{ChenLangeAndjelkovicetal.2022, author = {Chen, Junchao and Lange, Thomas and Andjelkovic, Marko and Simevski, Aleksandar and Lu, Li and Krstić, Miloš}, title = {Solar particle event and single event upset prediction from SRAM-based monitor and supervised machine learning}, series = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, volume = {10}, journal = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, number = {2}, publisher = {Institute of Electrical and Electronics Engineers}, address = {[New York, NY]}, issn = {2168-6750}, doi = {10.1109/TETC.2022.3147376}, pages = {564 -- 580}, year = {2022}, abstract = {The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.}, language = {en} } @article{KuehnHainzlDahmetal.2022, author = {K{\"u}hn, Daniela and Hainzl, Sebastian and Dahm, Torsten and Richter, Gudrun and Vera Rodriguez, Ismael}, title = {A review of source models to further the understanding of the seismicity of the Groningen field}, series = {Netherlands journal of geosciences : NJG}, volume = {101}, journal = {Netherlands journal of geosciences : NJG}, publisher = {Cambridge Univ. Press}, address = {Cambridge}, issn = {0016-7746}, doi = {10.1017/njg.2022.7}, pages = {12}, year = {2022}, abstract = {The occurrence of felt earthquakes due to gas production in Groningen has initiated numerous studies and model attempts to understand and quantify induced seismicity in this region. The whole bandwidth of available models spans the range from fully deterministic models to purely empirical and stochastic models. In this article, we summarise the most important model approaches, describing their main achievements and limitations. In addition, we discuss remaining open questions and potential future directions of development.}, language = {en} }