@article{13770, author = {{Karl, Holger and Kundisch, Dennis and Meyer auf der Heide, Friedhelm and Wehrheim, Heike}}, journal = {{Business & Information Systems Engineering}}, number = {{6}}, pages = {{467--481}}, publisher = {{Springer}}, title = {{{A Case for a New IT Ecosystem: On-The-Fly Computing}}}, doi = {{10.1007/s12599-019-00627-x}}, volume = {{62}}, year = {{2020}}, } @inproceedings{29298, abstract = {{Die Themen „Big Data“, „Künstliche Intelligenz und „Data Science“ werden seit einiger Zeit nicht nur in der breiten Öffentlichkeit kontrovers diskutiert, sondern stellen für die Ausbildung in den IT- und IT-nahen Berufen schon heute neue Herausforderungen dar, die in Zukunft durch die gesellschaftliche und technologische Weiterentwicklung hin zu einer Datengesellschaft noch größer werden. An dieser Stelle stellt sich die Frage, welche Aspekte dieses großen Themenkomplexes für Schule und Ausbildung von Wichtigkeit sind und wie diese Themen sinnstiftend und gewinnbringend in die informatische Ausbildung in verschiedenen Bildungsgängen integriert werden können. Im Rahmen des von uns im Jahr 2017 organisierten Symposiums zum Thema „Data Science“ wurden für die Bildung relevante Aspekte erörtert, wodurch als Kernelemente für den Unterricht Algorithmen der Künstlichen Intelligenz und ihre Anwendung in Industrie und Gesellschaft, Explorationen von Big Data sowie der Umgang mit eigenen Daten in sozialen Netzwerken herausgearbeitet wurden. Ziel ist, aus diesen Themenbereichen sowohl ein umfassendes Curriculum als auch Module für verschiedene Unterrichtsszenarien zu entwickeln und zu erproben. Durch diese Materialien soll es Lehrkräften aus der Informatik, Mathematik oder Technik ermöglicht werden, diese Themen auf Basis des Curriculums und der erprobten Unterrichtskonzepte selbst zu unterrichten. Hierfür wurde im Rahmen des Projekts ProDaBi (Projekt Data Science und Big Data in der Schule, https://www.prodabi.de), initiiert von der Telekom Stiftung, ein experimenteller Projektkurs entwickelt, den wir mit Schüler:innen der Sekundarstufe II an der Universität Paderborn im Schuljahr 2018/19 durchführten. Dieser Kurs enthält neben einem Modul zur Exploration von Big Data und einem weiteren Modul zum Maschinellen Lernen als Teil der Künstlichen Intelligenz auch eine Projektphase, die es in Zusammenarbeit mit lokalen Unternehmen den Schüler:innen ermöglicht, das Erlernte in ein reales Data Science-Projekt einzubringen. Aus den Erfahrungen dieses Projektkurses sowie den parallel durchgeführten Erprobungen einzelner Bausteine auch mit beruflichen Schulen werden ab dem Schuljahr 2019/20 die hierfür verwendeten Materialien weiterentwickelt und weiteren Kooperationspartnern zur Erprobung zur Verfügung gestellt. Damit wurden zum Ende des Projekts nicht nur vollständige Unterrichtsmaterialien, sondern auch ein umfassendes Curriculum entwickelt.}}, author = {{Opel, Simone Anna and Schlichtig, Michael}}, booktitle = {{Sammelband der 27. Fachtagung der BAG Berufliche Bildung}}, editor = {{Vollmer, Thomas and Karges, Torben and Richter, Tim and Schlömer, Britta and Schütt-Sayed, Sören}}, keywords = {{Berufsbildung, vocational education, Ausbildung, training, berufliche Weiterbildung, advanced vocational education, Digitalisierung, digitalization, Unterricht, teaching, Lehrmethode, teaching method, Interdisziplinarität, interdisciplinarity, Fachdidaktik, subject didactics, Curriculum, curriculum, gewerblich-technischer Beruf, vocational/technical occupation, Fachkraft, specialist, Qualifikationsanforderungen, qualification requirements, Kompetenz, competence, Lehrerbildung, teacher training, Bundesrepublik Deutschland, Federal Republic of Germany}}, location = {{Siegen}}, pages = {{176--194}}, publisher = {{wbv Media GmbH & Co. KG}}, title = {{{Data Science und Big Data in der beruflichen Bildung – Konzeption und Erprobung eines Projektkurses für die Sekundarstufe II}}}, doi = {{https://doi.org/10.3278/6004722w}}, volume = {{55}}, year = {{2020}}, } @inproceedings{3776, author = {{Chen, Wei-Fan and Al-Khatib, Khalid and Wachsmuth, Henning and Stein, Benno}}, booktitle = {{Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science}}, pages = {{149--154}}, title = {{{Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity}}}, year = {{2020}}, } @inproceedings{20137, author = {{Syed, Shahbaz and Chen, Wei-Fan and Hagen, Matthias and Stein, Benno and Wachsmuth, Henning and Potthast, Martin}}, booktitle = {{Proceedings of the 13th International Conference on Natural Language Generation (INLG 2020)}}, pages = {{237--241}}, title = {{{Task Proposal: Abstractive Snippet Generation for Web Pages}}}, year = {{2020}}, } @inproceedings{3818, author = {{Chen, Wei-Fan and Al-Khatib, Khalid and Stein, Benno and Wachsmuth, Henning}}, booktitle = {{Findings of the Association for Computational Linguistics: EMNLP 2020}}, pages = {{4290--4300}}, title = {{{Detecting Media Bias in News Articles using Gaussian Bias Distributions}}}, year = {{2020}}, } @inproceedings{15826, author = {{Chen, Wei-Fan and Syed, Shahbaz and Stein, Benno and Hagen, Matthias and Potthast, Martin}}, booktitle = {{Proceedings of the Web Conference 2020}}, pages = {{1309--1319}}, title = {{{Abstractive Snippet Generation}}}, year = {{2020}}, } @inproceedings{16868, author = {{Alshomary, Milad and Syed, Shahbaz and Potthast, Martin and Wachsmuth, Henning}}, booktitle = {{Proceedings of 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)}}, location = {{Seattle, USA}}, pages = {{4334--4345}}, publisher = {{Association for Computational Linguistics}}, title = {{{Target Inference in Argument Conclusion Generation}}}, year = {{2020}}, } @inproceedings{20141, author = {{Heindorf, Stefan and Scholten, Yan and Wachsmuth, Henning and Ngonga Ngomo, Axel-Cyrille and Potthast, Martin}}, booktitle = {{Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2020)}}, pages = {{3023--3030}}, title = {{{CauseNet: Towards a Causality Graph Extracted from the Web}}}, doi = {{10.1145/3340531.3412763}}, year = {{2020}}, } @misc{18638, author = {{Kramer, Paul}}, publisher = {{Universität Paderborn}}, title = {{{Comparison of Zero-Knowledge Range Proofs}}}, year = {{2020}}, } @inproceedings{20838, author = {{Lösch, Achim and Platzner, Marco}}, booktitle = {{2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)}}, isbn = {{9781728174457}}, title = {{{MigHEFT: DAG-based Scheduling of Migratable Tasks on Heterogeneous Compute Nodes}}}, doi = {{10.1109/ipdpsw50202.2020.00012}}, year = {{2020}}, } @inproceedings{13226, abstract = {{The canonical problem for the class Quantum Merlin-Arthur (QMA) is that of estimating ground state energies of local Hamiltonians. Perhaps surprisingly, [Ambainis, CCC 2014] showed that the related, but arguably more natural, problem of simulating local measurements on ground states of local Hamiltonians (APX-SIM) is likely harder than QMA. Indeed, [Ambainis, CCC 2014] showed that APX-SIM is P^QMA[log]-complete, for P^QMA[log] the class of languages decidable by a P machine making a logarithmic number of adaptive queries to a QMA oracle. In this work, we show that APX-SIM is P^QMA[log]-complete even when restricted to more physical Hamiltonians, obtaining as intermediate steps a variety of related complexity-theoretic results. We first give a sequence of results which together yield P^QMA[log]-hardness for APX-SIM on well-motivated Hamiltonians: (1) We show that for NP, StoqMA, and QMA oracles, a logarithmic number of adaptive queries is equivalent to polynomially many parallel queries. These equalities simplify the proofs of our subsequent results. (2) Next, we show that the hardness of APX-SIM is preserved under Hamiltonian simulations (a la [Cubitt, Montanaro, Piddock, 2017]). As a byproduct, we obtain a full complexity classification of APX-SIM, showing it is complete for P, P^||NP, P^||StoqMA, or P^||QMA depending on the Hamiltonians employed. (3) Leveraging the above, we show that APX-SIM is P^QMA[log]-complete for any family of Hamiltonians which can efficiently simulate spatially sparse Hamiltonians, including physically motivated models such as the 2D Heisenberg model. Our second focus considers 1D systems: We show that APX-SIM remains P^QMA[log]-complete even for local Hamiltonians on a 1D line of 8-dimensional qudits. This uses a number of ideas from above, along with replacing the "query Hamiltonian" of [Ambainis, CCC 2014] with a new "sifter" construction.}}, author = {{Gharibian, Sevag and Piddock, Stephen and Yirka, Justin}}, booktitle = {{Proceedings of the 37th Symposium on Theoretical Aspects of Computer Science (STACS 2020)}}, pages = {{38}}, title = {{{Oracle complexity classes and local measurements on physical Hamiltonians}}}, year = {{2020}}, } @inproceedings{46319, abstract = {{The detection of orchestrated and potentially manipulative campaigns in social media is far more meaningful than an- alyzing single account behaviour but also more challenging in terms of pattern recognition, data processing, and com- putational complexity. While supervised learning methods need an enormous amount of reliable ground truth data to find rather inflexible patterns, classical unsupervised learn- ing techniques need a lot of computational power to handle large amount of data. This makes them infeasible for real- time analysis. In this work, we demonstrate the applicability of text stream clustering for the real-time detection of coordi- nated campaigns.}}, author = {{Assenmacher, D and Adam, L and Trautmann, Heike and Grimme, C}}, booktitle = {{Proceedings of the Florida Artificial Intelligence Research Society Conference}}, title = {{{Towards Real-Time and Unsupervised Campaign Detection in Social Media}}}, year = {{2020}}, } @inproceedings{46328, abstract = {{In this paper, we rely on previous work proposing a modularized version of CMA-ES, which captures several alterations to the conventional CMA-ES developed in recent years. Each alteration provides significant advantages under certain problem properties, e.g., multi-modality, high conditioning. These distinct advancements are implemented as modules which result in 4608 unique versions of CMA-ES. Previous findings illustrate the competitive advantage of enabling and disabling the aforementioned modules for different optimization problems. Yet, this modular CMA-ES is lacking a method to automatically determine when the activation of specific modules is auspicious and when it is not. We propose a well-performing instance-specific algorithm configuration model which selects an (almost) optimal configuration of modules for a given problem instance. In addition, the structure of this configuration model is able to capture inter-dependencies between modules, e.g., two (or more) modules might only be advantageous in unison for some problem types, making the orchestration of modules a crucial task. This is accomplished by chaining multiple random forest classifiers together into a so-called Classifier Chain based on a set of numerical features extracted by means of Exploratory Landscape Analysis (ELA) to describe the given problem instances.}}, author = {{Prager, Raphael Patrick and Trautmann, Heike and Wang, Hao and Bäck, Thomas H. W. and Kerschke, Pascal}}, booktitle = {{Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI)}}, pages = {{996–1003}}, title = {{{Per-Instance Configuration of the Modularized CMA-ES by Means of Classifier Chains and Exploratory Landscape Analysis}}}, doi = {{10.1109/SSCI47803.2020.9308510}}, year = {{2020}}, } @inproceedings{46320, abstract = {{The identification of coordinated campaigns within Social Media is a complex task that is often hindered by missing labels and large amounts of data that have to be processed. We propose a new two-phase framework that uses unsupervised stream clustering for detecting suspicious trends over time in a first step. Afterwards, traditional offline analyses are applied to distinguish between normal trend evolution and malicious manipulation attempts. We demonstrate the applicability of our framework in the context of the final days of the Brexit in 2019/2020.}}, author = {{Assenmacher, D and Clever, L and Pohl, JS and Trautmann, Heike and Grimme, C}}, booktitle = {{Proceedings of the International Conference on Human-Computer Interaction (HCII 2020): Social Computing and Social Media. Design, Ethics, User Behavior, and Social Network Analysis}}, editor = {{Meiselwitz, G}}, isbn = {{978-3-030-49570-1}}, pages = {{201–214}}, publisher = {{Springer International Publishing}}, title = {{{A Two-Phase Framework for Detecting Manipulation Campaigns in Social Media}}}, doi = {{10.1007/978-3-030-49570-1_14}}, year = {{2020}}, } @inproceedings{46325, abstract = {{Clustering is an important technique in data analysis which can reveal hidden patterns and unknown relationships in the data. A common problem in clustering is the proper choice of parameter settings. To tackle this, automated algorithm configuration is available which can automatically find the best parameter settings. In practice, however, many of our today’s data sources are data streams due to the widespread deployment of sensors, the internet-of-things or (social) media. Stream clustering aims to tackle this challenge by identifying, tracking and updating clusters over time. Unfortunately, none of the existing approaches for automated algorithm configuration are directly applicable to the streaming scenario. In this paper, we explore the possibility of automated algorithm configuration for stream clustering algorithms using an ensemble of different configurations. In first experiments, we demonstrate that our approach is able to automatically find superior configurations and refine them over time.}}, author = {{Carnein, Matthias and Trautmann, Heike and Bifet, Albert and Pfahringer, Bernhard}}, booktitle = {{Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD ’19)}}, isbn = {{978-3-030-43823-4}}, pages = {{137–143}}, title = {{{Towards Automated Configuration of Stream Clustering Algorithms}}}, doi = {{10.1007/978-3-030-43823-4_12}}, year = {{2020}}, } @inproceedings{46321, abstract = {{Social bots have recently gained attention in the context of public opinion manipulation on social media platforms. While a lot of research effort has been put into the classification and detection of such automated programs, it is still unclear how technically sophisticated those bots are, which platforms they target, and where they originate from. To answer these questions, we gathered repository data from open source collaboration platforms to identify the status-quo of social bot development as well as first insights into the overall skills of publicly available bot code.}}, author = {{Assenmacher, Dennis and Frischlich , Lena and Trautmann, Heike and Grimme, Christian and Adam, Lena}}, booktitle = {{Disinformation in open online media}}, editor = {{Grimme, Christian and Preuß, Mike and Takes, Frank and Waldherr, Annie}}, pages = {{101–114}}, publisher = {{Springer}}, title = {{{Inside the tool set of automation: Free social bot code revisited}}}, year = {{2020}}, } @inproceedings{46326, abstract = {{Machine learning has become one of the most important tools in data analysis. However, selecting the most appropriate machine learning algorithm and tuning its hyperparameters to their optimal values remains a difficult task. This is even more difficult for streaming applications where automated approaches are often not available to help during algorithm selection and configuration. This paper proposes the first approach for automated algorithm selection and configuration of stream clustering algorithms. We train an ensemble of different stream clustering algorithms and configurations in parallel and use the best performing configuration to obtain a clustering solution. By drawing new configurations from better performing ones, we are able to improve the ensemble performance over time. In large experiments on real and artificial data we show how our ensemble approach can improve upon default configurations and can also compete with a-posteriori algorithm configuration. Our approach is considerably faster than a-posteriori approaches and applicable in real-time. In addition, it is not limited to stream clustering and can be generalised to all streaming applications, including stream classification and regression.}}, author = {{Carnein, Matthias and Trautmann, Heike and Bifet, Albert and Pfahringer, Bernhard}}, booktitle = {{Proceedings of the 14$^th$ Learning and Intelligent Optimization Conference (LION 2020)}}, pages = {{80–95}}, title = {{{confStream: Automated Algorithm Selection and Configuration of Stream Clustering Algorithms}}}, doi = {{10.1007/978-3-030-53552-0_10}}, year = {{2020}}, } @inproceedings{46327, abstract = {{In online media environments, nostalgia can be used as important ingredient of propaganda strategies, specifically, by creating societal pessimism. This work addresses the automated detection of nostalgic text as a first step towards automatically identifying nostalgia-based manipulation strategies. We compare the performance of standard machine learning approaches on this challenge and demonstrate the successful transfer of the best performing approach to real-world nostalgia detection in a case study.}}, author = {{Lena, Clever and Frischlich, Lena and Trautmann, Heike and Grimme, Christian}}, booktitle = {{Disinformation in open online media}}, editor = {{Grimme, Christian and Preuß, Mike and Takes, Frank and Waldherr, Annie}}, pages = {{48–58}}, title = {{{Automated detection of nostalgic text in the context of societal pessimism}}}, year = {{2020}}, } @inproceedings{46329, abstract = {{The past decade has been characterized by a strong increase in the use of social media and a continuous growth of public online discussion. With the failure of purely manual moderation, platform operators started searching for semi-automated solutions, where the application of Natural Language Processing (NLP) and Machine Learning (ML) techniques is promising. However, this requires huge financial investments for algorithmic implementations, data collection, and model training, which only big players can afford. To support smaller or medium-sized media enterprises (SME), we developed an integrated comment moderation system as an IT platform. This platform acts as a service provider and offers Analytics as a Service (AaaS) to SMEs. Operating such a platform, however, requires a robust technology stack, integrated workflows and well-defined interfaces between all parties. In this paper, we develop and discuss a suitable IT architecture and present a prototypical implementation.}}, author = {{Riehle, Dennis M. and Niemann, Marco and Brunk, Jens and Assenmacher, Dennis and Trautmann, Heike and Becker, Jörg}}, booktitle = {{Social Computing and Social Media. Participation, User Experience, Consumer Experience, and Applications of Social Computing}}, editor = {{Meiselwitz, Gabriele}}, isbn = {{978-3-030-49576-3}}, pages = {{71–86}}, publisher = {{Springer International Publishing}}, title = {{{Building an Integrated Comment Moderation System – Towards a Semi-automatic Moderation Tool}}}, year = {{2020}}, } @article{46333, abstract = {{ Recently, social bots, (semi-) automatized accounts in social media, gained global attention in the context of public opinion manipulation. Dystopian scenarios like the malicious amplification of topics, the spreading of disinformation, and the manipulation of elections through “opinion machines” created headlines around the globe. As a consequence, much research effort has been put into the classification and detection of social bots. Yet, it is still unclear how easy an average online media user can purchase social bots, which platforms they target, where they originate from, and how sophisticated these bots are. This work provides a much needed new perspective on these questions. By providing insights into the markets of social bots in the clearnet and darknet as well as an exhaustive analysis of freely available software tools for automation during the last decade, we shed light on the availability and capabilities of automated profiles in social media platforms. Our results confirm the increasing importance of social bot technology but also uncover an as yet unknown discrepancy of theoretical and practically achieved artificial intelligence in social bots: while literature reports on a high degree of intelligence for chat bots and assumes the same for social bots, the observed degree of intelligence in social bot implementations is limited. In fact, the overwhelming majority of available services and software are of supportive nature and merely provide modules of automation instead of fully fledged “intelligent” social bots. }}, author = {{Assenmacher, Dennis and Clever, Lena and Frischlich, Lena and Quandt, Thorsten and Trautmann, Heike and Grimme, Christian}}, journal = {{Social Media + Society}}, number = {{3}}, pages = {{2056305120939264}}, title = {{{Demystifying Social Bots: On the Intelligence of Automated Social Media Actors}}}, doi = {{10.1177/2056305120939264}}, volume = {{6}}, year = {{2020}}, }