Álvaro Figueira

Abstract
As social media (SM) becomes increasingly prevalent, its impact on society is expected to grow accordingly. While SM has brought positive transformations, it has also amplified pre-existing issues such as misinformation, echo chambers, manipulation, and propaganda. A thorough comprehension of this impact, aided by state-of-the-art analytical tools and by an awareness of societal biases and complexities, enables us to anticipate and mitigate the potential negative effects. One such tool is BERTopic, a novel deep-learning algorithm developed for Topic Mining, which has been shown to offer significant advantages over traditional methods like Latent Dirichlet Allocation (LDA), particularly in terms of its high modularity, which allows for extensive personalization at each stage of the topic modeling process. In this study, we hypothesize that BERTopic, when optimized for Twitter data, can provide a more coherent and stable topic modeling. We began by conducting a review of the literature on topic-mining approaches for short-text data. Using this knowledge, we explored the potential for optimizing BERTopic and analyzed its effectiveness. Our focus was on Twitter data spanning the two years of the 117th US Congress. We evaluated BERTopic's performance using coherence, perplexity, diversity, and stability scores, finding significant improvements over traditional methods and the default parameters for this tool. We discovered that improvements are possible in BERTopic's coherence and stability. We also identified the major topics of this Congress, which include abortion, student debt, and Judge Ketanji Brown Jackson. Additionally, we describe a simple application we developed for a better visualization of Congress topics.

Abstract
Static source code analysis techniques are gaining relevance in automated assessment of programming assignments as they can provide less rigorous evaluation and more comprehensive and formative feedback. These techniques focus on source code aspects rather than requiring effective code execution. To this end, syntactic and semantic information encoded in textual data is typically represented internally as graphs, after parsing and other preprocessing stages. Static automated assessment techniques, therefore, draw inferences from intermediate representations to determine the correctness of a solution and derive feedback. Consequently, achieving the most effective semantic graph representation of source code for the specific task is critical, impacting both techniques' accuracy, outcome, and execution time. This paper aims to provide a thorough comparison of the most widespread semantic graph representations for the automated assessment of programming assignments, including usage examples, facets, and costs for each of these representations. A benchmark has been conducted to assess their cost using the Abstract Syntax Tree (AST) as a baseline. The results demonstrate that the Code Property Graph (CPG) is the most feature -rich representation, but also the largest and most space -consuming (about 33% more than AST).

Abstract
This paper focuses on the creation and evaluation of synthetic data to address the challenges of imbalanced datasets in machine learning applications (ML), using fake news detection as a case study. We conducted a thorough literature review on generative adversarial networks (GANs) for tabular data, synthetic data generation methods, and synthetic data quality assessment. By augmenting a public news dataset with synthetic data generated by different GAN architectures, we demonstrate the potential of synthetic data to improve ML models’ performance in fake news detection. Our results show a significant improvement in classification performance, especially in the underrepresented class. We also modify and extend a data usage approach to evaluate the quality of synthetic data and investigate the relationship between synthetic data quality and data augmentation performance in classification tasks. We found a positive correlation between synthetic data quality and performance in the underrepresented class, highlighting the importance of high-quality synthetic data for effective data augmentation.

Abstract
Learning how to program is a difficult task. To acquire the re-quired skills, novice programmers must solve a broad range of programming activities, always supported with timely, rich, and accurate feedback. Automated assessment tools play a major role in fulfilling these needs, being a common pres-ence in introductory programming courses. As programming exercises are not easy to produce and those loaded into these tools must adhere to specific format requirements, teachers often opt for reusing them for several years. There-fore, most automated assessment tools, particularly Mooshak, store hundreds of submissions to the same programming ex-ercises, as these need to be kept after automatically pro-cessed for possible subsequent manual revision. Our dataset consists of the submissions to 16 programming exercises in Mooshak proposed in multiple years within the 2003-2020 timespan to undergraduate Computer Science students at the Faculty of Sciences from the University of Porto. In particular, we extract their code property graphs and store them as CSV files. The analysis of this data can enable, for instance, the generation of more concise and personalized feedback based on similar accepted submissions in the past, the identifica-tion of different strategies to solve a problem, the under -standing of a student's thinking process, among many other findings.(c) 2023 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )

Abstract
Learning to program requires diligent practice and creates room for discovery, trial and error, debugging, and concept mapping. Learners must walk this long road themselves, supported by appropriate and timely feedback. Providing such feedback in programming exercises is not a humanly feasible task. Therefore, the early and steadily growing interest of computer science educators in the automated assessment of programming exercises is not surprising. The automated assessment of programming assignments has been an active area of research for over a century, and interest in it continues to grow as it adapts to new developments in computer science and the resulting changes in educational requirements. It is therefore of paramount importance to understand the work that has been performed, who has performed it, its evolution over time, the relationships between publications, its hot topics, and open problems, among others. This paper presents a bibliometric study of the field, with a particular focus on the issue of automatic feedback generation, using literature data from the Web of Science Core Collection. It includes a descriptive analysis using various bibliometric measures and data visualizations on authors, affiliations, citations, and topics. In addition, we performed a complementary analysis focusing only on the subset of publications on the specific topic of automatic feedback generation. The results are highlighted and discussed.