Abstract
Symptoms-based detection of SARS-CoV-2 infection is not a substitute for precise diagnostic tests but can provide insight into the likely level of infection in a given population. This study uses symptoms data collected in the Global COVID-19 Trends and Impact Surveys (UMD Global CTIS), and data on variants sequencing from GISAID. This work, conducted in January of 2022 during the emergence of the Omicron variant (subvariant BA.1), aims to improve the quality of infection detection from the available symptoms and to use the resulting estimates of infection levels to assess the changes in vaccine efficacy during a change of dominant variant; from the Delta dominant to the Omicron dominant period. Our approach produced a new symptoms-based classifier, Random Forest, that was compared to a ground-truth subset of cases with known diagnostic test status. This classifier was compared with other competing classifiers and shown to exhibit an increased performance with respect to the ground-truth data. Using the Random Forest classifier, and knowing the vaccination status of the subjects, we then proceeded to analyse the evolution of vaccine efficacy towards infection during different periods, geographies and dominant variants. In South Africa, where the first significant wave of Omicron occurred, a significant reduction of vaccine efficacy is observed from August-September 2021 to December 2021. For instance, the efficacy drops from 0.81 to 0.30 for those vaccinated with 2 doses (of Pfizer/BioNTech), and from 0.51 to 0.09 for those vaccinated with one dose (of Pfizer/BioNTech or Johnson & Johnson). We also extended the study to other countries in which Omicron has been detected, comparing the situation in October 2021 (before Omicron) with that of December 2021. While the reduction measured is smaller than in South Africa, we still found, for instance, an average drop in vaccine efficacy from 0.53 to 0.45 among those vaccinated with two doses. Moreover, we found a significant negative (Pearson) correlation of around - 0.6 between the measured prevalence of Omicron in several countries and the vaccine efficacy in those same countries. This prediction, in January of 2022, of the decreased vaccine efficacy towards Omicron is in line with the subsequent increase of Omicron infections in the first half of 2022.

Abstract
Multiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.

Abstract

Abstract
Despite the increasing importance of business angels (BAs) as crucial players in the growth of high-potential early-stage startups, their motivations are not fully understood. Many of the perceptions of BAs deviate significantly from more conventional views of conventional economic and financial models. To gain a comprehensive understanding of BAs' goals, qualitative techniques from marketing and consumer behaviour as additional lenses (including laddering and means-ends chains) were employed to allow currently active BAs to articulate their goals in ways that forced-choice, quantitative methods do not achieve. Additionally, to determine if entrepreneurs perceive BAs in the same way BAs see themselves, entrepreneurs were asked to provide their perspectives on why BAs choose to become angel investors, based on their experiences with BAs. The findings reveal that traditional financial viewpoints do not adequately capture the depth and driving force behind BAs' goals, while entrepreneurs appear to be overly influenced by conventional assumptions about these goals. The study also provides valuable insights into the relationships and hierarchy among BAs' goals, and on the relevance of each goal. The paper ends with reflections on the practical implications of this research for BAs, entrepreneurs and policymakers.

Abstract
Africa is home to over 2,000 languages from more than six language families and has the highest linguistic diversity among all continents. These include 75 languages with at least one million speakers each. Yet, there is little NLP research conducted on African languages. Crucial to enabling such research is the availability of high-quality annotated datasets. In this paper, we introduce AfriSenti, a sentiment analysis benchmark that contains a total of >110,000 tweets in 14 African languages (Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yorùbá) from four language families. The tweets were annotated by native speakers and used in the AfriSenti-SemEval shared task ¹. We describe the data collection methodology, annotation process, and the challenges we dealt with when curating each dataset. We further report baseline experiments conducted on the different datasets and discuss their usefulness.

Abstract
Communication between Deaf and hearing individuals remains a persistent challenge requiring attention to foster inclusivity. Despite notable efforts in the development of digital solutions for sign language recognition (SLR), several issues persist, such as cross-platform interoperability and strategies for tokenizing signs to enable continuous conversations and coherent sentence construction. To address such issues, this paper proposes a non-invasive Portuguese Sign Language (Lingua Gestual Portuguesa or LGP) interpretation system-as-a-service, leveraging skeletal posture sequence inference powered by long-short term memory (LSTM) architectures. To address the scarcity of examples during machine learning (ML) model training, dataset augmentation strategies are explored. Additionally, a buffer-based interaction technique is introduced to facilitate LGP terms tokenization. This technique provides real-time feedback to users, allowing them to gauge the time remaining to complete a sign, which aids in the construction of grammatically coherent sentences based on inferred terms/words. To support human-like conditioning rules for interpretation, a large language model (LLM) service is integrated. Experiments reveal that LSTM-based neural networks, trained with 50 LGP terms and subjected to data augmentation, achieved accuracy levels ranging from 80% to 95.6%. Users unanimously reported a high level of intuition when using the buffer-based interaction strategy for terms/words tokenization. Furthermore, tests with an LLM-specifically ChatGPT-demonstrated promising semantic correlation rates in generated sentences, comparable to expected sentences.