Esports - games played competitively - comprise a major sector of the global games industry. Esports has been used as a testbed for game AI and game analytics for two decades. This article presents a multivocal literature mapping of available research that focuses strictly on the use of artificial intelligence approaches in Multiplayer Online Battle Arena (MOBA) games, one of the most popular esports genres and the one most widely used for game AI and game analytics research. A mapping is performed on relevant publications published between 2011 and 2022 and systematically examines them to extract similarities, gaps, and main findings. We analyzed 124 publications to identify the most studied topics, the most commonly used techniques, and the most commonly applied evaluation methods. The results show that League of Legends and DOTA are the most studied games, with outcome prediction being the most popular research topic. Finally, we provide an analysis of the potential future flagship areas for research in the domain, considering the gaps found in the white and grey literature.
Este artigo apresenta a formalização da metodologia utilizada pelos membros de um Laboratório de Ludologia para a criação de jogos com propósito. A metodologia é composta de um processo de cinco etapas: Concepção, Projeto, Produção, Avaliação e Empacotamento; além de ferramentas e práticas utilizadas durante a execução de suas tarefas. Ela foi definida considerando as experiências dos membros do laboratório na criação de artefatos lúdicos, outros trabalhos que explicitam os próprios processos para este mesmo fim, a análise da documentação gerada durante a produção de jogos e os registros das atividades (logs) desses processos. São apresentados três exemplos de sua aplicação na construção de jogos. Este artigo espera contribuir para a criação de novas metodologias de desenvolvimento de jogos com propósito, com maior dinamismo e colaboração entre os envolvidos, sejam pesquisadores, desenvolvedores, artistas ou projetistas.
Game development involves creating various content, from artistic tasks to technical activities. Procedural Content Generation (PCG) and metaheuristics like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) automate and optimize this process. This paper presents Dungeoncide, a game using GA and PSO for procedural content generation. Dungeoncide features a medieval knight battling monsters in procedural generated dungeons. The primary contributions include the development process and player feedback on the generated content’s quality and feasibility. Experiments showed that while generated levels were well-received, they were less challenging and immersive than manual ones. Future work will refine the algorithms to improve balance, aesthetics, and engagement.
Card games have long served as recreational tools across various cultures. This genre has also followed the trends of the digital gaming industry, with numerous games now featuring competitive scenes with substantial prizes, such as Legends of Runeterra. This paper proposes an automatic generator for competitive deck lineups in Legends of Runeterra, assessing extensive match databases using a Genetic Algorithm that evaluates candidate solutions based on three different generation strategies. This study introduces an evaluation function and presents empirical results concerning the effectiveness and efficiency of the approach. The findings indicate that the proposed method is useful and representative in a competitive context for all three addressed generation strategies.
A Engenharia de Requisitos é fundamental para qualidade dos softwares, porém o seu ensino possui diferentes desafios, entre eles, a falta de ferramentas de suporte específicas para disciplinas e a natureza colaborativa dessa atividade (que envolve diferentes stakeholders). Neste trabalho é apresentado um relato de experiência do ensino de Especificação de Requisitos em uma disciplina Requisitos de Software, na qual os alunos trabalharam com projetos reais utilizando práticas de metodologias ágeis com o suporte de uma nova ferramenta CASE colaborativa. Os resultados obtidos incluem as lições aprendidas e cerca de 68% dos alunos relataram dos feedbacks positivos. Requirements Engineering is fundamental for software quality, but teaching it has different challenges, including the lack of specific support tools for disciplines and the collaborative nature of this activity (which involves different stakeholders). This work presents an experience report of teaching Requirements Specification and Systems Modeling in a Software Requirements discipline, in which students worked with real projects using agile methodologies practices with the support of a new collaborative CASE tool. The results obtained include lessons learned and about 68% of students reported positive feedbacks. A Engenharia de Requisitos é fundamental para qualidade dos softwares, porém o seu ensino possui diferentes desafios, entre eles, a falta de ferramentas de suporte específicas para disciplinas e a natureza colaborativa dessa atividade (que envolve diferentes stakeholders). Neste trabalho é apresentado um relato de experiência do ensino de Especificação de Requisitos em uma disciplina Requisitos de Software, na qual os alunos trabalharam com projetos reais utilizando práticas de metodologias ágeis com o suporte de uma nova ferramenta CASE colaborativa. Os resultados obtidos incluem as lições aprendidas e cerca de 68% dos alunos relataram dos feedbacks positivos.
In this work, we explore the use of KNIME to identify toxic behavior in the MOBA game DOTA 2. Using a dataset composed of 10530 messages taken from 1903 matches, we tested the use of KNIME to identify toxic messages obtaining an accuracy of 92% and 85% for toxic and non-toxic messages, respectively. The DOTA 2 game chat log was used to present a low-code approach to a supervised learning model for message classification. In addition to providing insight into the toxic behavior of MOBA players, our work supports the idea that low-code development can reach levels as good as traditional development. On the other hand, our study can also serve as a basis for more elaborate implementations that allow us to observe other aspects of toxic behavior from its detection, encouraging the construction of prevention and neutralization tools.