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.

Abstract
This paper studies the state-of-the-art of active perception solutions for manipulation in agriculture and suggests a possible architecture for an active perception system for harvesting in agriculture. Research and developing robots for agricultural context is a challenge, particularly for harvesting and pruning context applications. These applications normally consider mobile manipulators and their cognitive part has many challenges. Active perception systems look reasonable approach for fruit assessment robustly and economically. This systematic literature review focus in the topic of active perception for fruits harvesting robots. The search was performed in five different databases. The search resumed into 1034 publications from which only 195 publications where considered for inclusion in this review after analysis. We conclude that the most of researches are mainly about fruit detection and segmentation in two-dimensional space using evenly classic computer vision strategies and deep learning models. For harvesting, multiple viewpoint and visual servoing are the most commonly used strategies. The research of these last topics does not look robust yet, and require further analysis and improvements for better results on fruit harvesting.

Abstract
Angola is characterized by many different languages and social, cultural and political realities, which had a marked effect on Angolan Portuguese (AP). Consequently, AP is characterized by diatopic variation. One of the marked effects is the loanwords imported from other Angolan languages. Our objective is to analyze different Angolan texts, analyze the lexical forms used and conduct a comparative study with European Portuguese, aiming at identifying the possible loanwords in Angolan Portuguese. This process was automated, as well as the identification of all loanwords' cotexts. In addition, we determine the lexical class of each loanword and the Angolan language of its origin. Most lexical loanwords come from the Kimbundu, although AP includes loanwords from some other Angolan languages too. Our study serves as a basis for preparing an Angolan regionalism dictionary. We noticed that more than 700 identified loanwords do not figure in the existing dictionaries.