Abstract

Abstract
Promoting active modes of transport, such as walking and cycling, has a positive impact on environmental sustainability and the health and well-being of citizens. This study explores the elderly population’s perception of comfort, safety and security when using active modes of transport. It begins with a systematic review of the literature considering research works that relate to active travel, the elderly population, and random forest. Then a questionnaire was applied to 653 participants and the results were analyzed. This analysis consisted of using statistics to evaluate the socio-demographic profile, the preferences regarding the use of active modes of this population, and the importance given to each dimension: comfort, safety, distance, and time, comparing these indicators through the Wilcoxon Rank Sum test and the Random Forest algorithm. The results showed that people over 56 years old walk as much as younger people. Furthermore, the importance given by this group of people to indicators referring to active modes is related to safety and security, distance, time, and comfort. The statistical results of the Wilcoxon Rank Sum test indicate the most important indicators: Adequate Travel Distance & Time and Existence of Commercial Areas by age group [0–55], and Absence of Allergenics and Existence of Green Areas by age group [56+]. Finally, the Random Forest algorithm provides the relative importance for both age groups, [0–55] and [56+], where the indicators that stand out in the [56+] age group, which is the focus of our study, are air quality, adequate travel distance & time, adequate crowd density, adequate thermal sensation, absence of allergenic, good street illumination level, adequate traffic volume, and adequate noise level.

Abstract
Online social networking platforms allow people to freely express their ideas, opinions, and emotions negatively or positively. Previous studies have examined sentiments on these platforms to study their behavior in different contexts and purposes. The mechanism of collecting public opinion information has attracted researchers to automatically classify the polarity of public opinions based on the use of concise language in messages, such as tweets, by analyzing social media data. In this paper, we extend the preceding work where an unsupervised approach to automatically detect extreme opinions/posts in social networks is proposed. The performance of the proposed approach is evaluated on five different social network and media datasets. In this work, we use a semi-supervised approach known as BERT to reevaluate the accuracy of our prior approach and the obtained classified dataset. The experiment proves that in these datasets, posts that were previously classified as negative or positive extreme are extremely negative or positive in many cases while using BERT. Furthermore, BERT shows the capability to classify the extreme sentiments when fine-tuned with an appropriate extreme sentiments dataset.

Abstract

Abstract
The need to take into account and explicitly model forecast uncertainty is today at the heart of many scientific and applied enterprises. For instance, the ever-increasing accuracy of weather forecasts has been driven by the development of ensemble forecasts, where a large number of forecasts are generated either by generating forecasts from different models or by repeatedly perturbing the initial conditions of a single forecast model. Importantly, this approach provides robust estimates of forecast uncertainty, which supports human judgement and decision-making. Although weather forecasts and their uncertainty are also crucial for the weather-to-power conversion for RES forecasting in system operation, power trading and balancing, the industry has been reluctant to adopt ensemble methods and other new technologies that can help manage highly variable and uncertain power feed-ins, especially under extreme weather conditions. In order to support the energy industry in the adaptation of uncertainty forecasts into their business practices, the IEA Wind Task 36 has started an initiative in collaboration with the Max Planck Institute for Human Development and Hans-Ertel Center for Weather Research to investigate the existing barriers in the industry to the adoption of such forecasts into decision processes. In the first part of the initiative, a forecast game was designed as a demonstration of a typical decision-making task in the power industry. The game was introduced in an IEA Wind Task 36 workshop and thereafter released to the public. When closed, it had been played by 120 participants. We will discuss the results of our first experience with the experiment and introduce some new features of the second generation of experiments as a continuation of the initiative. We will also discuss specific questions that emerged when we started and after analysing the experiments. Lastly we will discuss the trends we found and how we will fit these into the overall objective of the initiative which is to provide training tools to demonstrate the use and benefit of uncertainty forecasts by simulating decision scenarios with feedback and allowing people to learn from experience, rather than reading articles, how to use such forecasts.

Abstract
Traditional text classification approaches often require a good amount of labeled data, which is difficult to obtain, especially in restricted domains or less widespread languages. This lack of labeled data has led to the rise of low-resource methods, that assume low data availability in natural language processing. Among them, zero-shot learning stands out, which consists of learning a classifier without any previously labeled data. The best results reported with this approach use language models such as Transformers, but fall into two problems: high execution time and inability to handle long texts as input. This paper proposes a new model, ZeroBERTo, which leverages an unsupervised clustering step to obtain a compressed data representation before the classification task. We show that ZeroBERTo has better performance for long inputs and shorter execution time, outperforming XLM-R by about 12% in the F1 score in the FolhaUOL dataset.