检索结果-内蒙古大学图书馆

#StayHome playing LoL - Analyzing players' activity and social bonds in league of legends during covid-19 lockdowns

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Petrosino, Simone Loria, Enrica Pirker, Johanna Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Humans are social beings. It is therefore not surprising that the social distancing and movement restrictions associated with the Covid-19 pandemic had severe consequences for the well-being of large sections of the population, leading to increased loneliness and related mental diseases. Many people found emotional shelter in online multiplayer games, which have already proven to be great social incubators. While the positive effect games had on individuals has become evident, we are still unaware of how and if games fostered the fundamental need for connectedness that people sought. In other words: how have the social bonds and interaction patterns of players changed with the advent of the pandemic? For this purpose, we analyzed one year of data from an online multiplayer game (League of Legends) to observe the impact of Covid-19 on player assiduity and sociality in three different geographical regions (i.e., Europe, North America, and South Korea). Our results show a strong relationship between the development of Covid-19 restrictions and player activity, together with more robust and recurrent social bonds, especially for players committed to the game. Additionally, players with reinforced social bonds-i.e., people played with similar teammates-were more likely to stay in the game even once the restrictions were lifted. Copyright © 2021, The Authors. All rights reserved.

关键词： Geographical regions

4.2 Collaborating in a research and development project: Knowledge protection practices applied in a co-opetitive setting

学校读者我要写书评

暂无评论

4.2 Collaborating in a research and development project: Kno...

2019 Knowledge Management in Digital Work Environments State-of-the-Art and Outlook, WM 2019

作者： Kaiser, Rene Thalmann, Stefan Pammer-Schindler, Viktoria Fessl, Angela Know-Center - Research Center for Data-Driven Business and Big Data Analytics Graz Austria University of Graz Institute for Interactive Systems and Data Science Graz University of Technology Austria Know-Center and Institute for Interactive Systems and Data Science Graz University of Technology Austria

ISBN: (纸本)9783885796978

Organisations participate in collaborative projects that include competitors for a number of strategic reasons, even whilst knowing that this requires them to consider both knowledge sharing and knowledge protection throughout collaboration. In this paper, we investigated which knowledge protection practices representatives of organizations employ in a collaborative research and innovation project that can be characterized as a co-opetitive setting. We conducted a series of 30 interviews and report the following seven practices in structured form: restrictive partner selection in operative project tasks, communication through a gatekeeper, to limit access to a central platform, to hide details of machine data dumps, to have data not leave a factory for analysis, a generic model enabling to hide usage parameters, and to apply legal measures. When connecting each practice to a priori literature, we find three practices focussing on collaborative data analytics tasks had not yet been covered so far. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： data Analytics

The dynamics of diversity on corporate boards

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Raddant, Matthias Karimi, Fariba Graz University of Technology Institute of Software Technology Inffeldgasse 16b/II Graz8010 Austria University for Continuing Education Krems Department for Knowledge and Communication Management Dr.-Karl-Dorrek-Straße 30 Krems3500 Austria Graz University of Technology Institute of Interactive Systems and Data Science Sandgasse 36/III Graz8010 Austria Complexity Science Hub Vienna Josefstädter Straße 39 Vienna1080 Austria

Diversity in leadership positions, including corporate boards, is an important aspect of equality. It is important because it is the key to better decision-making and innovation, and above all, it paves the way for future generations to participate and shape our society. Many studies emphasize the importance of the visibility of role models and the effect that connectivity has on the success of minorities in leadership. However, the connectivity of firms, the dynamics of the adoption of minorities into leadership positions, and the long-term effects in terms of group dynamics and visibility are not well understood. Here, we present a model that shows how these effects work together in a dynamic model that is calibrated with empirical data of firm and board networks. We show that homophily - the appointment of minorities is influenced by the presence of minorities in a board and its neighboring entities - is an important effect shaping the trajectory towards equality. We further show how perception biases and feedback related to the visibility of minority members influence the dynamic. We find that reaching equality can be sped up or slowed down depending on the distribution of minorities in central firms. These insights bear significant implications for policy-making geared towards fostering equality and diversity within corporate boards. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

The data-driven business value matrix - a classification scheme for data-driven business models 32

学校读者我要写书评

暂无评论

The data-driven business value matrix - a classification sch...

32nd Bled eConference: Humanizing technology for a Sustainable Society, BLED 2019

作者： Breitfuss, Gert Fruhwirth, Michael Pammer-Schindler, Viktoria Stern, Hermann Dennerlein, Sebastian Know-Center Graz Austria University of Technology Institute for Interactive Systems and Data Science Graz Austria

ISBN: (纸本)9789612862800

Increasing digitization is generating more and more data in all areas of business. Modern analytical methods open up these large amounts of data for business value creation. Expected business value ranges from process optimization such as reduction of maintenance work and strategic decision support to business model innovation. In the development of a data-driven business model, it is useful to conceptualise elements of data-driven business models in order to differentiate and compare between examples of a data-driven business model and to think of opportunities for using data to innovate an existing or design a new business model. The goal of this paper is to identify a conceptual tool that supports data-driven business model innovation in a similar manner: We applied three existing classification schemes to differentiate between data-driven business models based on 30 examples for data-driven business model innovations. Subsequently, we present the strength and weaknesses of every scheme to identify possible blind spots for gaining business value out of data-driven activities. Following this discussion, we outline a new classification scheme. The newly developed scheme combines all positive aspects from the three analysed classification models and resolves the identified weaknesses. Copyright © 32nd Bled eConference Humanizing technology for a Sustainable Society, BLED 2019 - Conference Proceedings. All rights reserved.

关键词： Classification (of information)

Insights in Learners' Behaviour and Early Dropout Detection based on Coursera MOOCs 19

学校读者我要写书评

暂无评论

Insights in Learners' Behaviour and Early Dropout Detection ...

19th International Conference on Information technology Based Higher Education and Training, ITHET 2021

作者： Frank, Sarah Gutl, Christian Perez-Sanagustin, Mar Hilliger, Isabel Institute Of Interactive Systems And Data Science Graz University Of Technology Graz Austria Institute Recherche En Informatique De Toulouse Université Paul Sabatier Toulouse France School Of Engineering Pontificia Universidad Católica De Chile Santiago Chile

ISBN: (纸本)9781728188836

Increased utilization of distance learning makes the creation of effective learning tools ever more important. However, while Massive Open Online Courses (MOOCs) are a popular online learning tool, they often suffer from high user attrition. This paper investigated this effect for 6 different MOOCs with more than 35 thousand users, using AdaBoosted decision trees to create a model which was then used for the prediction of dropouts, as well as the calculation of feature importance scores. The resulting model generally scored high accuracy scores which were plotted for each course, and feature importance scores were especially high for the features encompassing the number of user requests, the user's total active time and the average time between clicks. Furthermore, the paper explored the results of the inclusion of forum data in this setting. While the forum features did not lead to a major increase in model accuracy, there was a statistical difference between the number of forum interactions for those who completed the MOOCs and those who did not, which opens up possibilities for future research into utilization of forum interaction data, and forums in MOOCs in general. © 2021 IEEE.

关键词： Decision trees

Predicting Partial Discharges of Transformers: Decision Support System for Factory Acceptance Test

学校读者我要写书评

暂无评论

Predicting Partial Discharges of Transformers: Decision Supp...

IEEE International Conference on Industrial Engineering and Engineering Management

作者： B. Gigerl Y. Zhao J. Raminger J. Bakakeu R. Kern S. Thalmann Department of Process Digitalization Siemens Energy Weiz Austria Department of Manufacturing Technology Siemens Energy Nürnberg Germany Department of Test Field Siemens Energy Weiz Austria Department of Sales Engineering Alteryx München Germany Institute of Interactive Systems and Data Science Technical University of Graz Graz Austria Institute of Operations and Information Systems University of Graz Graz Austria

Partial discharges, mainly caused by an insufficient drying processes or different types of contamination, reduce the lifetime of a transformer, and thus lead to expensive rework costs. Herein, a decision support system for partial discharges of transformers occurring in oven and filling processes is introduced. Based on machine learning (ML), partial discharge results are evaluated in dependency of various manufacturing parameters and an automated prediction tool to guide the production with preventive actions is developed. The required data, obtained from sensors and manufacturing sources, is used to train supervised learning algorithms that aim to predict and classify partial discharges. To achieve adequate accuracy and reliability, multiple ML and data mining techniques are applied, including feature engineering, clustering, and final evaluation of performance by cost factors. The evaluation results show that the introduced ML models effectively detect and classify early test failures in oven and filling processes, resulting in a successful identification of key factors and consequently to more efficient action derivation. Overall, the potential of decision support systems as a valuable tool in the field of transformers is emphasized.

关键词：

Constraint 2021: Machine learning models for COVID-19 fake news detection shared task

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Felber, Thomas Institute of Interactive Systems and Data Science Graz University of Technology Inffeldgasse 13 Graz8010 Austria

In this system paper we present our contribution to the Constraint 2021 COVID-19 Fake News Detection Shared Task, which poses the challenge of classifying COVID-19 related social media posts as either fake or real. In our system, we address this challenge by applying classical machine learning algorithms together with several linguistic features, such as n-grams, readability, emotional tone and punctuation. In terms of pre-processing, we experiment with various steps like stop word removal, stemming/lemmatization, link removal and more. We find our best performing system to be based on a linear SVM, which obtains a weighted average F1 score of 95.19% on test data, which lands a place in the middle of the leaderboard (place 80 of 167). © 2021, CC BY.

关键词： Classification (of information)

Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Razouk, Houssam Benischke, Leonie Gärber, Daniel Kern, Roman Quality Management Infineon Technologies Austria AG Carinthia Villach9500 Austria Institute of Interactive Systems and Data Science Graz University of Technology Styria Graz8010 Austria Centre de Recherches Interdisciplinaires et Transculturelles Université Bourgogne Franche-Comté Besançon Franche-Comté25000 France Know-Center GmbH Styria Graz8010 Austria

The extraction of causal information from textual data is crucial in the industry for identifying and mitigating potential failures, enhancing process efficiency, prompting quality improvements, and addressing various operational challenges. This paper presents a study on the development of automated methods for causal information extraction from actual industrial documents in the semiconductor manufacturing industry. The study proposes two types of causal information extraction methods, single-stage sequence tagging (SST) and multistage sequence tagging (MST), and evaluates their performance using existing documents from a semiconductor manufacturing company, including presentation slides and FMEA (Failure Mode and Effects Analysis) documents. The study also investigates the effect of representation learning on downstream tasks. The presented case study showcases that the proposed MST methods for extracting causal information from industrial documents are suitable for practical applications, especially for semi structured documents such as FMEAs, with a 93% F1 score. Additionally, MST achieves a 73% F1 score on texts extracted from presentation slides. Finally, the study highlights the importance of choosing a language model that is more aligned with the domain and in-domain fine-tuning. © 2024, CC BY.

关键词： Natural language processing systems

Testing robustness of predictions of trained classifiers against naturally occurring perturbations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Scher, Sebastian Trügler, Andreas Know-Center GmbH Inffeldgasse 13/6 Graz8010 Austria Institute of Interactive Systems and Data Science Graz University of Technology Inffeldgasse 16C Graz8010 Austria Department of Geography and Regional Science University of Graz Heinrichstraße 36 Graz8010 Austria

Correctly quantifying the robustness of machine learning models is a central aspect in judging their suitability for specific tasks, and ultimately, for generating trust in them. We address the problem of finding the robustness of individual predictions. We show both theoretically and with empirical examples that a method based on counterfactuals that was previously proposed for this is insufficient, as it is not a valid metric for determining the robustness against perturbations that occur "naturally", outside specific adversarial attack scenarios. We propose a flexible approach that models possible perturbations in input data individually for each application. This is then combined with a probabilistic approach that computes the likelihood that a "real-world" perturbation will change a prediction, thus giving quantitative information of the robustness of individual predictions of the trained machine learning model. The method does not require access to the internals of the classifier and thus in principle works for any black-box model. It is, however, based on Monte-Carlo sampling and thus only suited for input spaces with small dimensions. We illustrate our approach on the Iris and the Ionosphere datasets, on an application predicting fog at an airport, and on analytically solvable cases. Copyright © 2022, The Authors. All rights reserved.

关键词： Ionosphere