Teses

Creativity is known as an ability that can be developed and improved. Since creative abilities are desired in most modern societies, it becomes important to develop activities that stimulate creativity at a very young age. It seems, however, there is a lack of tools to support creative activities for children. We present Cubus, a tool that uses autonomous synthetic characters to stimulate idea generation in groups of children during a storytelling activity. With Cubus, children can invent a story and use the stop-motion technique to create a movie depicting it. This work yielded a useful methodology that we consider can aid the design of tools which assist users in their task. This methodology consists in an iterative development where several user studies are carried out to inform and validate design choices during a tool's different development stages. Additionally, a methodology to evaluate the different aspects of creativity is also presented and implemented during our creativity evaluation with Cubus. To evaluate how Cubus supports creativity, we investigated the number of ideas generated by groups of children during their creative process of creating and recording a story and the creativity of the product this process originated, a stop-motion movie. Results showed that the embodied synthetic characters with autonomous behavior of Cubus contributed to the generation of more ideas in children, a key aspect of creativity. Regarding the creative product, results suggest that Cubus agents' autonomous behaviors were unable to influence children's creative products, the stop-motion movies.

O processamento de Língua Natural é uma área complexa de engenharia informática. Nos últimos anos, a Lígua Natural começou a ter mais interacção com a área de Jogos e foi estabelecida em conjunto com o reconhecimento de fala. Esta tese de Dissertação de mestrado abrange a teoria de um agente inteligente artificial capaz de jogar o Jogo Lobisomem ou Mafia, com uma interação mais natural com os jogadores humanos, usando técnicas de processamento de Língua Natural e Teoria de Probabilidade. Apresentamos nossa solução para criar esse agente, onde tomamos partido das redes bayesianas, do algoritmo de eliminação variável, de um agente conversacional incorporado e de medidas de similaridade.

Personality has been a key feature in the creation of companion characters for digital games. These characters cooperate with the player to overcome obstacles and progress through the game. In this work, we present a generic framework and a personality model inspired by Cloninger's psychobiological model of Temperament and Character to convey a companion character’s personality in the context of the cooperation between the companion character and the player. Our framework is comprised of the character's personality, a decision system based on the character's personality, and a tag system to keep track of the character's experience, knowledge, objectives, etc. We conducted a two-stage experiment to better understand (1) if the character's graphical design has an influence on personality reporting and (2) if the companion's personality conveyed by our model is adequately perceived by the player through interaction. Our results suggest that (1) in-game behaviour is more important than first impressions induced by the character's design and that (2) two of our traits (Harm Avoidance and Cooperativeness) were easily understood by the participants.

Neste trabalho é proposta uma abordagem com base nos métodos Monte-Carlo, para o jogo Hearthstone: Heróis de Warcraft, o jogo de cartas colecionáveis mais popular do momento e com mais de 50 milhões de jogadores registados em Abril de 2016. No Hearthstone, os jogadores são continuamente posto á prova devido ao conceito de informação escondida, onde a mão do oponente é desconhecida, devido ao conceito de aleatoriedade existente, onde por exemplo as cartas são inicialmente baralhadas e devido a uma complexa jogabilidade, que muitas vezes requer uma estratégia bastante robusta e refinada. Com o trabalho desenvolvido, argumentamos que, á luz dos desafios colocados pelo jogo (conceito de informação escondida e incerteza), a abordagem desenvolvida para o efeito oferece uma alternativa valida, face ao atual estado da arte neste domínio. Adicionalmente, através do enriquecimento do algoritmo, mais especificamente através da introdução de informação especifica do jogo, é possível alcançar ganhos significativos de desempenho, relativamente a sua versão mais tradicional.