Search

The novel coronavirus (SARS-CoV-2) has rapidly developed into a global epidemic. To control its spread, countries have implemented non-pharmaceutical interventions (NPIs), such as school closures, bans of small gatherings, or even stay-at-home orders. Here we study the effectiveness of seven NPIs in reducing the number of new infections, which was inferred from the reported cases of COVID-19 using a semi-mechanistic Bayesian hierarchical model. Based on data from the first epidemic wave of n = 20 countries (i.e., the United States, Canada, Australia, the EU-15 countries, Norway, and Switzerland), we estimate the relative reduction in the number of new infections attributed to each NPI. Among the NPIs considered, bans of large gatherings were most effective, followed by venue and school closures, whereas stay-at-home orders and work-from-home orders were least effective. With this retrospective cross-country analysis, we provide estimates regarding the effectiveness of different NPIs during the first epidemic wave., PLoS ONE, 16 (6), ISSN:1932-6203

State-of-the-art question answering (QA) relies upon large amounts of training data for which labeling is time consuming and thus expensive. For this reason, customizing QA systems is challenging. As a remedy, we propose a novel framework for annotating QA datasets that entails learning a cost-effective annotation policy and a semi-supervised annotation scheme. The latter reduces the human effort: it leverages the underlying QA system to suggest potential candidate annotations. Human annotators then simply provide binary feedback on these candidates. Our system is designed such that past annotations continuously improve the future performance and thus overall annotation cost. To the best of our knowledge, this is the first paper to address the problem of annotating questions with minimal annotation cost. We compare our framework against traditional manual annotations in an extensive set of experiments. We find that our approach can reduce up to 21.1% of the annotation cost., Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), ISBN:978-1-952148-60-6

BackgroundThe novel coronavirus (SARS-CoV-2) has rapidly evolved into a global epidemic. To control its spread, countries have implemented non-pharmaceutical interventions (NPIs), such as school or border closures, while others have even enforced complete lockdowns. Here we study the impact of NPIs in reducing documented cases of COVID-19. Documented case numbers are selected because they are essential for decision-makers in the area of health-policy when monitoring and evaluating current control mechanisms.MethodsWe empirically estimate the relative reduction in the number of new cases attributed to each NPI. A cross-country analysis is performed using documented cases through April 15, 2020 from n = 20 countries (i.e., the United States, Canada, Australia, the EU-15 countries, Norway, and Switzerland).ResultsAs of April 15, venue closures were associated with a reduction in the number of new cases by 36 % (95% credible interval [CrI] 20–48 %), closely followed by gathering bans (34 %; 95% CrI 21–45 %), border closures (31 %; 95% CrI 19–42 %), and work bans on non-essential business activities (31 %; 95% CrI 16–44 %). Event bans lead to a slightly less pronounced reduction (23 %; 95% CrI 8–35 %). School closures (8 %; 95% CrI 0–23 %) and lockdowns (5 %; 95% CrI 0–14 %) appeared to be the least effective among the NPIs considered in this analysis.ConclusionsWith this cross-country analysis, we provide early estimates regarding the impact of different NPIs for controlling the COVID-19 epidemic. These findings are relevant for evaluating current health-policies.

Emotions widely affect human decision-making. This fact is taken into account by affective computing with the goal of tailoring decision support to the emotional states of individuals. However, the accurate recognition of emotions within narrative documents presents a challenging undertaking due to the complexity and ambiguity of language. Performance improvements can be achieved through deep learning; yet, as demonstrated in this paper, the specific nature of this task requires the customization of recurrent neural networks with regard to bidirectional processing, dropout layers as a means of regularization, and weighted loss functions. In addition, we propose sent2affect, a tailored form of transfer learning for affective computing: here the network is pre-trained for a different task (i.e. sentiment analysis), while the output layer is subsequently tuned to the task of emotion recognition. The resulting performance is evaluated in a holistic setting across 6 benchmark datasets, where we find that both recurrent neural networks and transfer learning consistently outperform traditional machine learning. Altogether, the findings have considerable implications for the use of affective computing., Comment: Accepted by Decision Support Systems (DSS)

Enterprise resource planning (ERP) systems are often cumbersome to customize to a client's needs. Model-driven approaches promise to simplify these attempts. In this work we present an ERP prototype based on the Resource-Event-Agent (REA) business ontology that follows a "model-at-runtime" approach: one may customize the ERP system during runtime by changing the underlying REA models. We are using Retail-H as the reference framework for building a retail information system(RIS). Our main contribution is the prototypical implementation of a domain agnostic REA engine that can be loaded at runtime with domain specific business models -- these models can further be manipulated at runtime. On that basis we have exemplarily modeled main concepts of Retail-H in REA. Validation of the implemented components is realized by applying real business activities and requirements received from our partner, a business software solution provider.

Often, there is a lack of efficient procedures in order to identify design errors when transforming customer requirements into servic-oriented solution. A well-established approach supporting this kind of transformation in classical requirements engineering is the traceability matrix which allows tracing the coverage of customer requirements by system components in general, or services in particular. The matrix shows which services realize which customer requirements. However, the matrix does not show the relevance of a service in order to meet a certain quality aspect (e.g. Security, usability, maintainability, etc.). Since this information is not explicitly covered, it is the system designer who has to keep this knowledge in mind when designing an appropriate set of services that build the overall system. Unfortunately, stakeholders not involved in the design decisions, e.g. Customers, Project managers and developers, have a hard time to understand the significance of the coverage of customer requirements by services in order to meet desired quality aspects. This may cause misinterpretations especially in the early stages of the service system development life-cycle. In this paper, we present a heuristic-based approach to continually monitor and control design decisions and their effects on certain quality aspects. This approach extends the traceability matrix by a weighted decision-matrix.