This study investigates the dynamics between traditional media companies and emerging digital actors during the 2018 Brazilian Presidential Elections through a comprehensive analysis of Twitter communications. Using Latent Dirichlet Allocation (LDA) topic modeling, we analyzed 4,366,960 tweets from 892,105 users during the period of October 26–30, 2018, focusing on shared links and content from the top 20 media outlets. The research reveals that while established media companies maintained their dominant position in terms of content distribution (with 10 out of 20 top-shared domains), partisan and alternative media outlets successfully challenged their narrative. This study contributes to agenda-setting theory by quantifying how digital platforms enable alternative media to compete with traditional outlets for narrative control in political discourse, despite resource disparities.

Interdisciplinarity (Pombo, 2004a, b, 2005) refers to a method or mindset that merges concepts and methods in order to arrive at new approaches and solutions in scientific research and education. This convergence, along with problem-solving strategy, can be attained by mixing several scientific disciplines, namely when we face hard and complex problems.

Introduction/Purpose Noncontrast CT (NCCT) is the first line screening modality to evaluate for intracerebral hemorrhage (ICH) and early ischemic changes in the setting of acute ischemic stroke (AIS). Large vessel occlusions (LVOs) are a major cause of AIS, but challenging to detect on NCCT alone. The purpose of this study is to evaluate a fully-automated AI platform called RAPID NCCT Stroke (iSchemaView, Menlo Park, CA) for ICH and LVO detection as compared to expert neuroimaging readers. Materials and Methods In this IRB approved retrospective, multicenter study, 244 patients with suspected acute stroke were included. Stand-alone performance of the RAPID NCCT Stroke platform was assessed (based on the consensus of 3 neuroradiologists who determined reference standard from CT/CTA) and sensitivity and specificity were determined. The platform's performance was then compared to expert interpretation by neuroimaging readers comprised of eight general radiologists (GR) and three neuroradiologists (NR) in detecting ICH and hyperdense vessel sign (HVS) as a marker of LVO. The primary hypothesis was that the sensitivity of RAPID NCCT Stroke for detection of LVO would be superiority to GR readers and non-inferiority to NR readers. Receiver operating characteristics (ROC) curve was used to evaluate the performance of each reader based on a rating system from 1 to 5 to express confidence in LVO detection. P < 0.05 was considered significant. Results A total of 244 cases were included in this study. Of the 244, 115 were LVOs and 26 were ICHs. One hundred three cases did not have LVO nor ICH. Stand-alone performance of the platform demonstrated sensitivities and specificities of 96.2% and 99.5% respectively for ICH as well as 63.5% and 95.1% for LVO detection. In assessing non-inferiority of the platform compared to all 11 readers, the platform achieved a significantly higher sensitivity (63.5% versus 43.6%, p < 0.0001), meeting criteria for both non-inferiority and superiority. When compared to the eight GR readers only, the platform also showed superiority with significantly higher sensitivity (63.5% versus 40.9%, p = 0.001). Conclusion The RAPID NCCT Stroke platform demonstrated superior performance to radiologists for detecting LVO from a NCCT. This could lead to earlier identification of LVO and faster treatment times. Prospective studies are needed for further validation. Disclosures V. Yedavalli: 2; C; RAPID (iSchemaview, Menlo Park, CA). J. Heit: 2; C; RAPID (iSchemaview, Menlo Park, CA). S. Dehkharghani: None. H. Haerian: None. J. McMenamy: None. J. Honce: None. V. Timpone: None. C. Harnain: None. A. Kesselman: None. A. Filly: None. A. Beardsley: None. B. Sakamoto: None. C. Song: None. J. Montuori: None. B. Navot: None. F. Mena: None. D. Giurguitiu: None. F. Kitamura: None. F. Lima: None. H. Coelho: None. F. Mont'Alverne: None. G. Albers: 4; C; RAPID (IschemaView, Menlo Park, CA).

Technologies such as Artificial Intelligence (Analytics and Automation) can harm purposely persons (via fake news of social networks, drones, robots, apps, platforms) without any available regulations and forms of protection. We need not only benefits to offer to everybody but responsible ways to develop all new intelligent systems, and agents without high risks and strange behaviours. In many cases, decisions are not intelligible to humans and easy explanations are not available anywhere. We want diverse technologies to aid people and deliver great advantages to society at large.

The digital learning transformation brings the extension of the traditional libraries to online repositories. Learning object repositories are employed to deliver several functionalities related to the learning object’s lifecycle. However, these educational resources usually are not described effectively, lacking, for example, educational metadata and learning goals. Then, metadata incompleteness limits the quality of the services, such as search and recommendation, resulting in educational objects that do not have a proper role in teaching/learning environments. This work proposes to bring an active role to all educational resources, acting on the analysis generated from the usage statistics. To achieve this goal, we created a multi-agent architecture that complements the common repository’s functionalities to improve learning and teaching experiences. We intend to use this architecture on a repository focused on ocean literacy learning objects. This paper presents some steps toward this goal by enhancing, when needed, the repository to adapt itself.

While Artificial intelligence technologies continue to proliferate in all areas of contemporary life, researchers are looking for ways to make them safe for users. In the teaching-learning context, this is a trickier problem because it must be clear which principles or ethical frameworks are guiding processes supported by artificial intelligence. After all, people education are at stake. This inquiry presents an approach to value alignment, in educational contexts using artificial pedagogical moral agents (AMPA) adopting the classic BDI model. Besides, we propose a top-down approach explaining why the bottom-up or the hybrid one may would not be advisable in educational grounds.

The humans are affective and cognitive beings relying on memories for their individual and social identities. Also, human dyadic bonds require some common beliefs such as empathetic behaviour for better interaction. In this sense, research studies involving human-agent interaction should resource on affect, cognition, and memory integration. The developed artificial agent system (SensAI+Expanse) includes machine learning algorithms, heuristics, and memory as cognition aids towards emotional valence prediction on the interacting human. Further, an adaptive empathy score is always present in order to engage the human in a recognisable interaction outcome. [...] The agent is resilient on collecting data, adapts its cognitive processes to each human individual in a learning best effort for proper contextualised prediction. The current study make use of an achieved adaptive process. Also, the use of individual prediction models with specific options of the learning algorithm and evaluation metric from a previous research study. The accomplished solution includes a highly performant prediction ability, an efficient energy use, and feature importance explanation for predicted probabilities. Results of the present study show evidence of significant emotional valence behaviour differences between some age ranges and gender combinations. Therefore, this work contributes with an artificial intelligent agent able to assist on cognitive science studies. This ability is about affective disturbances by means of predicting human emotional valence contextualised in space and time. Moreover, contributes with learning processes and heuristics fit to the task including economy of cognition and memory to cope with the environment. Finally, these contributions include an achieved age and gender neutrality on predicting emotional valence states in context and with very good performance for each individual.

Autonomous Vehicles (AVs), from autonomy level 3 to 5 are expected to enter the EU market within a year and our infrastructures, as well as legal and social systems are hardly prepared to deal with this technology, which continues to advance rapidly right in front of us. The main purpose of this article is to critically analyse, from a cognitive science point of view, merging AI, philosophy and law, what has been done in this domain and what else requires immediate attention in order to allow AVs to perform a safe and uneventful entry in our society.

An agent, artificial or human, must be continuously adjusting its behaviour in order to thrive in a more or less demanding environment. An artificial agent with the ability to predict human emotional valence in a geospatial and temporal context requires proper adaptation to its mobile device environment with resource consumption strict restrictions (e.g., power from battery). The developed distributed system includes a mobile device embodied agent (SensAI) plus Cloud-expanded (Expanse) cognition and memory resources. The system is designed with several adaptive mechanisms in a best effort for the agent to cope with its interacting humans and to be resilient on collecting data for machine learning towards prediction. These mechanisms encompass homeostatic-like adjustments such as auto recovering from an unexpected failure in the mobile device, forgetting repeated data to save local memory, adjusting actions to a proper moment (e.g., notify only when human is interacting), and the Expanse complementary learning algorithms' parameters with auto adjustments. Regarding emotional valence prediction performance, results from a comparison study between state-of-the-art algorithms revealed Extreme Gradient Boosting on average the best model for prediction with efficient energy use, and explainable using feature importance inspection. Therefore, this work contributes with a smartphone sensing-based system, distributed in the Cloud, robust to unexpected behaviours from humans and the environment, able to predict emotional valence states with very good performance.

This paper investigates first-level agenda-setting effects on Twitter during UK's EU referendum campaign. Using topic-modeling techniques, we investigate the dynamics of the interaction between users and the media content, and how the media outlets relate to each other. Results show that traditional media outlets dominated the debate, but alternative media played an important part. The media outlets that supported “Leave” stood closer to users' opinion who contributed to polarize the media's message, with pro-Leave side successfully framing some media's message in his own terms.

After the involvement with a huge collection of case studies, where the experimentation may distinguish between luck and skill, our motivation was directed to see how agent-based modeling and model thinking were applied to general problem solving and case studies on complexity. Also, the development of models was directed to show the efficacy of diversity in attacking new scenarios and landscapes. And, even we avoided often Nassim Taleb’s mantra, “we tend to learn the overall precise and not the general”, the desire was to get realism (avoid embellished depiction of nature and behavior). This direction of research forced our attention upon the calibration of parameters, the validation, the use of mechanisms, the use of big data, and the activity of scaling up to check the plausibility of the outcomes.

Agent technology is a relatively new and rapidly expanding area of research and development. The major motivations for the increasing interest in intelligent agents and multi-agent systems include the ability to provide solutions to problems that can naturally be regarded as a society of autonomous interacting components, to solve problems that are too large for a centralized agent to solve, and to provide solutions in situations where expertise is distributed. Electricity markets (EMs) are complex distributed systems, typically involving a variety of transactive techniques (e.g., centralized and bilateral market clearing). The agent-based approach is an ideal fit to the naturally distributed domain of EMs. Accordingly, a number of agent-based models and systems for EMs have been proposed in the technical literature. These models and systems exhibit fairly different features and make use of a diverse range of concepts. At present, there seems to be no agreed framework to analyze and compare disparate research efforts. Chapter 2 and this companion chapter claim that such a framework can be very important and instructive, helping to understand the interrelationships of disparate research efforts. Accordingly, Chap. 2 (Part I) and this chapter (Part II) introduce a generic framework for agent-based simulation of EMs. The complete framework includes three groups (or categories) of dimensions: market architecture, market structure and software agents. The first two groups were the subject of Chap. 2. This chapter discusses in considerable detail the last group of dimensions, labeled "software agents", and composed by two distinct yet interrelated dimensions: agent architectures and agent capabilities.

A Simulação Social refere-se ao uso de métodos computacionais e analíticos, baseados na Ciência da Complexidade e na Ciência dos Dados e, ainda, no rigor matemático para melhorar a compreensão dos sistemas sociais (por exemplo, alguns problemas nacionais, como a mobilidade urbana e os transportes, a crise financeira global, a saúde pública, ou a educação).

Along this decade, advances from Cognitive and Computing Sciences disturbed the college campus, namely, via the availability of online courses (MOOCs) and tools, and also the secondary schools with e-learning environments. The technological impacts helped to democratize traditional university education and brought, to everywhere in the world, the teaching of wonderful professors through Internet (YouTube). Yet, the lectures are still alive, and the old fashion pedagogy seems in good health, most of the students do not participate fully in the process of learning. What is missing is a profound shake-up of mentalities, new initiatives to accelerate learning research and the discovery of the resilience of the whole process. Artificial intelligence and information and communication technologies (ICTs) in general are sound proposals to open alleys till a happy solution, and in this study, we try to show some ideas about the disruption of the traditional classroom scenario due to the availability of innovative online resources and computers (tablets, smartphones, and laptops).

We present an Agent-Based model called ProtestLab for the simulation of street protests, with multiple types of agents (protesters, police and ‘media’) and scenario features (attraction points, obstacles and entrances/exits). In ProtestLab agents can have multiple “personalities” (implemented via agent subtypes), goals and possible states, including violent confrontation. The model includes quantitative measures of emergent crowd patterns, protest intensity, police effectiveness and potential ‘news impact’, which can be used to compare simulation outputs with estimates from videos of real protests for parametrization and validation. ProtestLab was applied to a scenario of policemen defending a government building from protesters (typical of anti-austerity protests in front of the Parliament in Lisbon, Portugal) and reproduced many features observed in real events, such as clustering of ‘active’ and ‘violent’ protesters, formation of moving confrontation lines, occasional fights and arrests, ‘media’ agents wiggling around ‘hot spots’ and policemen with defensive or offensive behaviour.

In some recent works, it was shown that any algorithmic description might be mapped on a recurrent neural network. A neural oriented language called NETDEF, such that each program corresponds to a modular neural net that computes it, is the tool to achieve this. This article focuses on merging symbolic and subsymbolic computation. Adding high-order neurons to the network model allows learning integration into the NETDEF symbolic computing paradigm, since it is possible to execute learning algorithms in the same neural model that performs symbolic computation. It is shown how the model may process competitive learning methods inside this framework.

The electricity industry has evolved to open marketsthat promote competition among suppliers and provide consumers with a choice of services. Most energy markets (EMs) were, however, designed without the notion that a significant part of the traded power could come from renewable energy sources, and may require modifications to continue functioning effectively. Agent-based modeling and simulation (ABMS) presents itself as a promising approach to accurately model the behavior of EMs over time. This article claims that the development of a conceptual framework to define the key features that are needed to model and simulate EMs using software agents can be an important step to assess progress in the field and highlight new avenues to explore. As a first step in this direction, it describes a category of dimensions, labeled "market architecture", of a conceptual framework for agent-based electricity markets.