Abstract
Economic and Food Safety Authority receives on a daily basis reports and complaints regarding infractions, delicts and possible food and economic crimes. These reports and complaints can be in different forms, such as e-mails, online forms, letters, phone calls and complaint books present in every establishment. This paper aims to apply text mining and classification algorithms to textual data extracted from these reports and complains in order to help identify if the responsible entity to analyze the content is, in fact, the Economic and Food Safety Authority. The paper describes text preprocessing and feature extraction procedures applied to Portuguese text data. Supervised multi-class classification methods such as Naïve Bayes and Support Vector Machine Classifiers are employed in the task. We show that a non-semantical text mining approach can achieve good results, scoring around 70% of accuracy.

Abstract

Abstract
This paper analyses the directions and causes of student migration in the information society at economic universities in Poland and Portugal. An international survey was conducted among students born between 1981 and 1995. The research included a group of 121 Polish and 55 Portuguese students. The conclusions of the study confirm the hypothesis that the place of residence/country of origin has a significant effect on the direction of migration. Furthermore, the causes of migration are largely dependent on the gender of the respondents and their professional status.

Abstract
This paper proposes a "grey-box" dynamic equivalent model for medium voltage active distribution networks, taking into account a heterogeneous fleet of generation technologies alongside the latest European grid codes requirements. It aims to properly represent the transient behavior of the system upon large voltage disturbances in the transmission side. The proposed equivalent model is composed by four main components: two equivalent generation units, one for converter-connected units' representation, and another accounting for the synchronous generation units' portfolio; an equivalent composite load model; and a battery energy storage system, also converter-connected to the grid. The model's parameters are estimated by an evolutionary particle swarm optimization algorithm, by comparing a fully-detailed model of a medium voltage distribution network with the equivalent model's frequency domain's responses of active and reactive power flows, at the boundary of distribution-transmission interface substation.

Abstract
Dendro, a research data management (RDM) platform developed at FEUP/INESC TEC since 2014, was initially targeted at collaborative data storage and description in preparation for deposit in any data repository (CKAN, Zenodo, ePrints or B2Share). We implemented our own data deposit and dataset search features, consolidating the whole RDM workflow in Dendro: dataset exporting, automatic DOI attribution, and a dataset faceted search, among other features. We discuss the challenges faced when implemented these features and how they make Dendro more FAIR.

Abstract
In order to investigate the factors influencing the sustainable guarantee network and its differences in different spatial and temporal scales, logistic regression algorithm is used to analyze the data of listed companies in 31 provinces, municipalities and autonomous regions in China from 2008 to 2017 (excluding Hong Kong, Macau and Taiwan). The study finds that, overall, companies with better profitability, poor solvency, poor operational capability and higher levels of economic development are more likely to join the guarantee network. On the temporal scale, solvency and regional economic development exert increasing higher impact on the companies' accession to the guarantee network, and operational capacity has increasingly smaller impact. On the spatial scale, the less close link between company executives and companies in the western region suggests higher possibility to join the guarantee network. The predictive accuracy test results of the logistic regression algorithm show that the training model of the western sample enterprises has the highest prediction accuracy when predicting enterprise behavior of joining the guarantee network, while the accuracy is the lowest in the central region. When forecasting enterprises' failure to join the guarantee network, the training model of the central sample enterprise has the highest accuracy, while the accuracy is the lowest in the eastern region. This paper discusses the internal and external factors influencing the guarantee network risk from the perspective of spatial and temporal differences of the guarantee network, and discriminates the prediction accuracy of the training model, which means certain guiding significance for listed company management, bank and government to identify and control the guarantee network risk.