Engineering Design (ED) is a complex process in which the reuse of knowledge is crucial: applying the knowledge consolidated in previous design activities to future design activities means performing them in a better ...
详细信息
Engineering Design (ED) is a complex process in which the reuse of knowledge is crucial: applying the knowledge consolidated in previous design activities to future design activities means performing them in a better way. The relevance of data in ED is even more crucial in a business context in which data Science (DS) is literally revolutionizing the way companies operate and therefore also the way data are analyzed. Despite having been recognized as crucial for ED processes, data still remain closed in the domain and accessible only to their owners due to several constraints related to the private and proprietary nature of the acquired data. An answer to these challenges could be found in opendata, but at the state of the art an operational Engineering Design framework to embrace them is still far to be achieved by both academia and industry. Given these issues, the aim of this paper is to give evidence that Text Mining can help to make a complex opendatabase more effective to be used for the ED process, taking U.S. open Government data (OGD) repository as a case study. open access to methods and data used within this research is provided. The results of this study allow us to understand for which purposes it is possible to apply the datasets and to comprehend the expertise and the data science methods needed for processing different data for-mats. Moreover, this work opens relevant implications and challenges for researchers, practitioners and policy makers operating in ED and DS domains that could become opportunities for future research and industrial applications. (c) 2022 Elsevier B.V. All rights reserved.
This paper presents an exhaustive and unified repository of judgments documents, called ECHR-OD , based on the European Court of Human Rights. The need of such a repository is explained through the prism of the resear...
详细信息
This paper presents an exhaustive and unified repository of judgments documents, called ECHR-OD , based on the European Court of Human Rights. The need of such a repository is explained through the prism of the researcher, the data scientist, the citizen, and the legal practitioner. Contrarily to many opendata repositories, the full creation process of ECHR-OD , from the collection of raw data to the feature transformation, is provided by means of a collection of fully automated and open-source scripts. It ensures reproducibility and a high level of confidence in the processed data, which is one of the most important issues in data governance nowadays. The experimental evaluation was performed to study the problem of predicting the outcome of a case, and to establish baseline results of popular machine learning algorithms. The obtained results are consistently good across the binary datasets with an accuracy comprised between 75.86% and 98.32%, having the average accuracy equals to 96.45%, which is 14pp higher than the best known result with similar methods. We achieved a F1-Score of 82% which is aligned with the recent result using BERT. We show that in a multilabel setting, the features available prior to a judgment are good predictors of the outcome, opening the road to practical applications. (C) 2021 Elsevier Ltd. All rights reserved.
暂无评论