Pedro O. S. Vaz-De-Melo

Thiago Magrin, Jordan Kobellarz, Pedro O. S. Vaz-de-Melo et al.

Political news on social media rarely circulates in isolation: audiences actively engage, react, and clash. Whether these interactions reflect agreement or conflict may depend on the ideological discrepancy between publishers and the news content they share. This study investigates this relationship using Facebook posts linking to political news during a Brazilian presidential election. We analyze five dimensions of engagement: ideological discrepancy between publishers and content, emotional responses, audience consensus, toxicity in posts, and content topics. Our results show that ideological discrepancy is associated with differences in engagement, exhibiting a nonlinear pattern: consensus declines under conditions of very high ideological mismatch and, in our data, also under very high alignment, while toxicity increases primarily under extreme mismatch. A statistical model indicates that emotional valence, toxicity, and ideological discrepancy are the factors most strongly associated with consensus. Among highly partisan publishers, higher toxicity is associated with increased audience consensus, suggesting that hostile discourse may co-occur with in-group agreement in strongly ideological contexts. Overall, these findings highlight how ideological discrepancy, emotional reactions, and interaction dynamics are associated with consensus and polarization in online political engagement.

Gustavo Lúcius Fernandes, Jeiverson C. V. M. Santos, Pedro O. S. Vaz-de-Melo

Large language models (LLMs) are increasingly used to assess moral or ethical statements, yet their judgments may reflect social and linguistic biases. This work presents a controlled, sentence-level study of how grammatical person, number, and gender markers influence LLM moral classifications of fairness. Starting from 550 balanced base sentences from the ETHICS dataset, we generated 26 counterfactual variants per item, systematically varying pronouns and demographic markers to yield 14,850 semantically equivalent sentences. We evaluated six model families (Grok, GPT, LLaMA, Gemma, DeepSeek, and Mistral), and measured fairness judgments and inter-group disparities using Statistical Parity Difference (SPD). Results show statistically significant biases: sentences written in the singular form and third person are more often judged as "fair'', while those in the second person are penalized. Gender markers produce the strongest effects, with non-binary subjects consistently favored and male subjects disfavored. We conjecture that these patterns reflect distributional and alignment biases learned during training, emphasizing the need for targeted fairness interventions in moral LLM applications.

Túlio Marcondes Moreira, Jackson Geraldo de Faria, Pedro O. S. Vaz-de-Melo et al.

In this work, an AI-Driven (autonomous) model representation of the La Rance tidal barrage was developed using novel parametrisation and Deep Reinforcement Learning (DRL) techniques. Our model results were validated with experimental measurements, yielding the first Tidal Range Structure (TRS) model validated against a constructed tidal barrage and made available to academics. In order to proper model La Rance, parametrisation methodologies were developed for simulating (i) turbines (in pumping and power generation modes), (ii) transition ramp functions (for opening and closing hydraulic structures) and (iii) equivalent lagoon wetted area. Furthermore, an updated DRL method was implemented for optimising the operation of the hydraulic structures that compose La Rance. The achieved objective of this work was to verify the capabilities of an AI-Driven TRS model to appropriately predict (i) turbine power and (ii) lagoon water level variations. In addition, the observed operational strategy and yearly energy output of our AI-Driven model appeared to be comparable with those reported for the La Rance tidal barrage. The outcomes of this work (developed methodologies and DRL implementations) are generalisable and can be applied to other TRS projects. Furthermore, this work provided insights which allow for more realistic simulation of TRS operation, enabled through our AI-Driven model.

Niander Assis, Renato Assunção, Pedro O. S. Vaz-De-Melo

Timeout is a short interruption during games used to communicate a change in strategy, to give the players a rest or to stop a negative flow in the game. Whatever the reason, coaches expect an improvement in their team's performance after a timeout. But how effective are these timeouts in doing so? The simple average of the differences between the scores before and after the timeouts has been used as evidence that there is an effect and that it is substantial. We claim that these statistical averages are not proper evidence and a more sound approach is needed. We applied a formal causal framework using a large dataset of official NBA play-by-play tables and drew our assumptions about the data generation process in a causal graph. Using different matching techniques to estimate the causal effect of timeouts, we concluded that timeouts have no effect on teams' performances. Actually, since most timeouts are called when the opposing team is scoring more frequently, the moments that follow resemble an improvement in the team's performance but are just the natural game tendency to return to its average state. This is another example of what statisticians call the regression to the mean phenomenon.