Abstract
Assessment plays a central role in any educational process as a way of evaluating the students' knowledge on the concepts associated with learning objectives. The assessment of free-text answers is a process that, besides being very costly in terms of time spent by teachers, may lead to inequities due to the difficulty in applying the same evaluation criteria to all answers. This paper describes a system composed by several modules whose main goal is to work as a formative assessment tool for students and to help teachers creating and assessing exams as well monitoring students' progress. The system automatically creates training exams for students to practice based on questions from previous exams and assists teachers in the creation of evaluation exams with various kinds of information about students' performance. The system automatically assesses training exams to give automatic feedback to students. The correction of free-text answers is based on the syntactic and semantic similarity between the student answers and various reference answers, thus going beyond the simple lexical matching. For this, several pre-processing tasks are performed in order to reduce each answer to its more manageable canonical form. Besides the syntactic and semantic similarity between answers, the way the teacher evaluates the answers is also acquired. To accomplish that, the assessment is done using sub scores defined by the teacher concerning parts of the answer or its subgoals. The system has been trained and tested on exams manually graded by History teachers. There is a good correlation between the evaluation of the instructors and the evaluation performed by our system.

Abstract
This paper presents a comprehensive study on the application of machine learning techniques in the prediction of respiratory rate via time-series-based statistical and machine learning methods using several physiological signals. Two different models, ARIMA and LSTM, were developed. The LSTM model showed a stronger capacity for learning and capturing complicated patterns in the data compared to the ARIMA model. The findings imply that LSTM models, by incorporating many variables, have the ability to provide predictions that are more accurate, particularly in situations where respiratory rate values vary significantly. © 2024 The Authors. Published by ELSEVIER B.V.

Abstract
The intrinsic challenges of contemporary marketing encourage discovering new approaches to engage and retain customers effectively. As the main channels of interactions between customers and brands pivot between the physical and the digital world, analyzing the outcome behavioral patterns must be achieved dynamically with the stimulus performed in both poles. This systematic review investigates the collaborative impact of adopting multidisciplinary fields of Affective Computing to evaluate current marketing strategies, upholding the process of using multimodal information from consumers to perform and integrate Sentiment Analysis tasks. The adjusted representation of modalities such as textual, visual, audio, or even psychological indicators enables prospecting a more precise assessment of the advantages and disadvantages of the proposed technique, glimpsing future applications of Multimodal Artificial Intelligence in Marketing. Embracing the Preferred Reporting Items for Systematic Reviews and Meta-Analysis as the research method to be applied, this article warrants a rigorous and sequential identification and interpretation of the synergies between the latest studies about affective computing and marketing. Furthermore, the robustness of the procedure is deepened in knowledge-gathering concerning the current state of Affective Computing in the Marketing area, their technical practices, ethical and legal considerations, and the potential upcoming applications, anticipating insights for the ongoing work of marketers and researchers.

Abstract
The cryptocurrency market presents immense opportunities and significant risks due to its high volatility. Accurate price forecasting is crucial for informed investment decisions, enabling investors to optimize portfolio allocation, mitigate risk, and potentially maximize returns. Existing forecasting methods often struggle with the inherent non-stationarity and complexity of cryptocurrency price dynamics. This study addresses this challenge by developing a system for high-frequency forecasting of the closing prices of ten leading cryptocurrencies. We compare various machine learning models, including recurrent neural networks (RNNs), time series analysis (ARIMA), and conventional regression algorithms, using minute-step Bitcoin price data over a 30-day period to predict prices 60 min ahead. Our findings demonstrate that the GRU neural network exhibits superior predictive accuracy (MAPE = 0.09%, MSE = 5954.89, RMSE = 77.17, MAE = 60.20), outperforming other models considered. This improved forecasting accuracy contributes to the existing literature by providing empirical evidence for GRU's effectiveness in the volatile cryptocurrency market and offers practical insights for investment strategies. A web application integrating the best-performing model further facilitates real-time price prediction for multiple cryptocurrencies.

Abstract
Stress in the workplace is a major problem that affects people of all ages, backgrounds, and occupations. It can contribute to various health problems, from anxiety to insomnia, among others. Workplace stress significantly impacts employee well-being and productivity. Current stress-management approaches, while valuable, primarily address stress after it has occurred. This highlights the critical need for proactive systems capable of anticipating individual stress and preventing negative health consequences. This research presents the design and initial implementation of a novel microservice-based recommendation system for proactively mitigating workplace stress among computer users. The system leverages predicted stress levels to deliver timely, personalized, and easily implemented interventions. This study focuses on evaluating the system's architecture, core functionalities, and initial performance using a content-based filtering approach. A pilot study demonstrated the system's feasibility, highlighting areas for future development.

Abstract
This study presents a machine learning-based approach to predicting the outcosmes of NBA games, with the aim of enhancing decision-making in sports betting and performance analysis. Using a dataset spanning 20 NBA seasons (2003-2023), we incorporated key features such as team statistics, player performance metrics, and external factors like team fatigue and rankings. The methodology followed the CRISP-DM process, involving data preprocessing, feature selection, and model evaluation. We experimented with multiple classification algorithms, including Logistic Regression, Random Forest, Gradient Boosting, and ensemble methods, to identify the best-performing models. Feature selection techniques such as LASSO and decision tree-based methods were employed to optimize model performance. Our best model, combining team rankings, statistics, and fatigue factors, achieved an accuracy rate of 64.1% and an F1 score of 72.4%, reflecting the complexity of NBA game outcome prediction. The study highlights the importance of key features like team rankings and the challenges posed by the dynamic nature of the NBA. Future research will explore additional qualitative factors, such as emotional states and team dynamics, and employ more advanced machine learning techniques like deep learning to further improve prediction accuracy. © 2025 F Rodrigues et al., published by Sciendo.