Please use this identifier to cite or link to this item:
Author(s): Bruno Xavier Faria Tavares
Title: Emotional Agents for Shooter Games: Understanding How Players' Emotional Profiles Influence Game Playouts
Issue Date: 2015-07-07
Abstract: Gameplay testing still suffers from inefficient feedback assimilation, not only due to the subjective nature of the retrieved information but also due to the amount of time required to retrieve it. This work attempts to ameliorate that issue by automating the testing process without losing all emotional data. We aim to achieve this by modeling an agent to replicate expected human behaviors. The models are created based on previously collected data from actual gameplay sessions, translated into Arousal and Valence values, through fuzzy clustering. With this proof of concept, we expect to emulate human behaviors in a satisfactory manner and evaluate the usefulness of this method as a quality assurance tool.
Description: This project attempts to improve on game testing practices by using human behaviour modelling techniques applied on artificial intelligence agents. By mapping responses to events to variations in Arousal and Valence values, we can cluster those responses and develop a regression model that emulates a cluster members' response to those events, which we can map back to certain types of behaviours , such as evading the enemy. To prove this, we will conduct both a simplified Turing Test, based on captured footage of playthroughs by Humans and AI Agents, as well as comparing simulation parameters, such as accuracy and time taken, to see how closely the AI Agent can emulate human behaviour. To facilitate this, a simulator representative of the games is also developed.
Subject: Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
Scientific areas: Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática
Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
TID identifier: 201298562
Document Type: Dissertação
Rights: openAccess
Appears in Collections:FEUP - Dissertação

Files in This Item:
File Description SizeFormat 
35291.pdfEmotional Agents for Shooter Games: Understanding How Players' Emotional Profiles Influence Game Playouts7.64 MBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons