2022
Roohi, Shaghayegh
Advances in AI-assisted game testing Väitöskirja
Tietotekniikka, Aalto-yliopisto, 2022, ISBN: 978-952-64-0825-5.
Abstract | Links | BibTeX | Avainsanat: AI agents, emotion recognition, englanninkieliset väitöskirjat, game testing, player experience, reinforcement learning
@phdthesis{Roohi2022,
title = {Advances in AI-assisted game testing},
author = {Shaghayegh Roohi},
url = {http://urn.fi/URN:ISBN:978-952-64-0825-5},
isbn = {978-952-64-0825-5},
year = {2022},
date = {2022-01-01},
school = {Tietotekniikka, Aalto-yliopisto},
abstract = {Game testing is an essential part of game development, in which developers try to select a game design that delivers a desirable experience for the players and engages them. However, the interactive nature of games makes the player experience and behavior unpredictable. Therefore, game testing requires collecting a large amount of playtest data in iterative sessions, which makes game testing time and money consuming.
Game testing includes a wide range of aspects from finding bugs and balancing game parameters to modeling player behavior and experience. This dissertation mostly concentrates on the player experience aspect. It proposes methods for (partially) automating and facilitating the game testing process. The first part of the dissertation focuses on player emotion analysis and proposes tools and methods for automatically processing and summarizing human playtesters' data. The second part of the dissertation concentrates on simulation-based approaches for modeling player experience and behavior to reduce the need for human playtesters.
In the first publication, we use deep neural networks for analyzing player facial expression data and provide a visualization tool for inspecting affect changes at game events, which replicates earlier results of physiological emotion analysis. Next, we extend this work by introducing a new dataset of game streamers' emotions in different granularities and considering other input signals like audio and speech for automatic emotion recognition. In the second part of the dissertation, simulation-based methods and reinforcement learning agents are used to predict game difficulty and engagement and capture the relation between these two game metrics.
In summary, this dissertation proposes and evaluates methods that advance automatic game testing by proposing approaches for automatic analysis of player emotions, which can be used for selecting specific segments of playtest videos for further inspection. In addition, we have provided accurate models of player experience and behavior using simulation-based methods that can be used to detect problematic game levels before releasing them to the actual players.},
keywords = {AI agents, emotion recognition, englanninkieliset väitöskirjat, game testing, player experience, reinforcement learning},
pubstate = {published},
tppubtype = {phdthesis}
}
Game testing is an essential part of game development, in which developers try to select a game design that delivers a desirable experience for the players and engages them. However, the interactive nature of games makes the player experience and behavior unpredictable. Therefore, game testing requires collecting a large amount of playtest data in iterative sessions, which makes game testing time and money consuming.
Game testing includes a wide range of aspects from finding bugs and balancing game parameters to modeling player behavior and experience. This dissertation mostly concentrates on the player experience aspect. It proposes methods for (partially) automating and facilitating the game testing process. The first part of the dissertation focuses on player emotion analysis and proposes tools and methods for automatically processing and summarizing human playtesters' data. The second part of the dissertation concentrates on simulation-based approaches for modeling player experience and behavior to reduce the need for human playtesters.
In the first publication, we use deep neural networks for analyzing player facial expression data and provide a visualization tool for inspecting affect changes at game events, which replicates earlier results of physiological emotion analysis. Next, we extend this work by introducing a new dataset of game streamers' emotions in different granularities and considering other input signals like audio and speech for automatic emotion recognition. In the second part of the dissertation, simulation-based methods and reinforcement learning agents are used to predict game difficulty and engagement and capture the relation between these two game metrics.
In summary, this dissertation proposes and evaluates methods that advance automatic game testing by proposing approaches for automatic analysis of player emotions, which can be used for selecting specific segments of playtest videos for further inspection. In addition, we have provided accurate models of player experience and behavior using simulation-based methods that can be used to detect problematic game levels before releasing them to the actual players.
Game testing includes a wide range of aspects from finding bugs and balancing game parameters to modeling player behavior and experience. This dissertation mostly concentrates on the player experience aspect. It proposes methods for (partially) automating and facilitating the game testing process. The first part of the dissertation focuses on player emotion analysis and proposes tools and methods for automatically processing and summarizing human playtesters' data. The second part of the dissertation concentrates on simulation-based approaches for modeling player experience and behavior to reduce the need for human playtesters.
In the first publication, we use deep neural networks for analyzing player facial expression data and provide a visualization tool for inspecting affect changes at game events, which replicates earlier results of physiological emotion analysis. Next, we extend this work by introducing a new dataset of game streamers' emotions in different granularities and considering other input signals like audio and speech for automatic emotion recognition. In the second part of the dissertation, simulation-based methods and reinforcement learning agents are used to predict game difficulty and engagement and capture the relation between these two game metrics.
In summary, this dissertation proposes and evaluates methods that advance automatic game testing by proposing approaches for automatic analysis of player emotions, which can be used for selecting specific segments of playtest videos for further inspection. In addition, we have provided accurate models of player experience and behavior using simulation-based methods that can be used to detect problematic game levels before releasing them to the actual players.
2020
Bopp, Julia Ayumi
Tietojenkäsittelytiede, Aalto-yliopisto, 2020, ISBN: 978-952-64-0112-6 .
Abstract | Links | BibTeX | Avainsanat: aesthetic emotion, emotion, englanninkieliset väitöskirjat, games, player experience
@phdthesis{Bopp2020,
title = {Aesthetic emotions in digital games: The appeal of moving, challenging, and thought-provoking player experiences},
author = {Julia Ayumi Bopp},
url = {http://urn.fi/URN:ISBN:978-952-64-0112-6},
isbn = {978-952-64-0112-6 },
year = {2020},
date = {2020-01-01},
school = {Tietojenkäsittelytiede, Aalto-yliopisto},
abstract = {Film, music, literature, and the visual arts are all acclaimed for their capacity to afford emotionally rich experiences, including aesthetic emotions typically considered negative and challenging. Games, in contrast, have been argued to be less effective at evoking a similarly broad spectrum of emotions due to their inherent focus on gameplay and mechanics. Concurrently, efforts in player-computer interaction have mostly concentrated on fun, flow, and need satisfaction. As a consequence, several empirical and conceptual gaps in our understanding of the player experience remain: We know little about what kind of aesthetic emotions players feel, to what extent they value such experiences, how games evoke these emotions, and what the outcomes of such experiences may be.
This thesis addresses these research gaps in five empirical studies. Results from Publication I, Publication II, and Publication III showcase that players experience a range of aesthetic emotions in games, typically associated with other art forms. Games also afford unique aesthetic emotions, such as remorse and a sense of responsibility. Publication I and Publication III highlight that players enjoy and appreciate such aesthetic emotional experiences, in some instances, precisely because of games evoking intense negative feelings. Moreover, Publication I, Publication II, and Publication III identify means through which games facilitate aesthetic emotions, including tough decisions, as well as attachment to and loss of game characters. Players' personal experiences and memories also shape the gaming experience, highlighting how games can profoundly impact players in different ways. Notably, Publication IV showcases games' potential for affording aesthetic epistemic emotions, experiences that prompt reflection on the self and others. Finally, Publication V provides insights on how a VR game specifically designed to stimulate reflection fostered understanding and empathy for others in distress, both in-game and in real-life.
This thesis contributes to empirical and conceptual problem-solving in player-computer interaction. First, it provides empirically based descriptions of the hitherto little explored phenomenon of aesthetic emotions in games and their potential outcomes. Second, it contributes to a more nuanced understanding of positive player experience and helps to clarify concepts such as emotional challenge and character attachment. Finally, the thesis highlight game aspects that play an important role in affording aesthetic emotional experiences, and outlines avenue for future research.},
keywords = {aesthetic emotion, emotion, englanninkieliset väitöskirjat, games, player experience},
pubstate = {published},
tppubtype = {phdthesis}
}
Film, music, literature, and the visual arts are all acclaimed for their capacity to afford emotionally rich experiences, including aesthetic emotions typically considered negative and challenging. Games, in contrast, have been argued to be less effective at evoking a similarly broad spectrum of emotions due to their inherent focus on gameplay and mechanics. Concurrently, efforts in player-computer interaction have mostly concentrated on fun, flow, and need satisfaction. As a consequence, several empirical and conceptual gaps in our understanding of the player experience remain: We know little about what kind of aesthetic emotions players feel, to what extent they value such experiences, how games evoke these emotions, and what the outcomes of such experiences may be.
This thesis addresses these research gaps in five empirical studies. Results from Publication I, Publication II, and Publication III showcase that players experience a range of aesthetic emotions in games, typically associated with other art forms. Games also afford unique aesthetic emotions, such as remorse and a sense of responsibility. Publication I and Publication III highlight that players enjoy and appreciate such aesthetic emotional experiences, in some instances, precisely because of games evoking intense negative feelings. Moreover, Publication I, Publication II, and Publication III identify means through which games facilitate aesthetic emotions, including tough decisions, as well as attachment to and loss of game characters. Players' personal experiences and memories also shape the gaming experience, highlighting how games can profoundly impact players in different ways. Notably, Publication IV showcases games' potential for affording aesthetic epistemic emotions, experiences that prompt reflection on the self and others. Finally, Publication V provides insights on how a VR game specifically designed to stimulate reflection fostered understanding and empathy for others in distress, both in-game and in real-life.
This thesis contributes to empirical and conceptual problem-solving in player-computer interaction. First, it provides empirically based descriptions of the hitherto little explored phenomenon of aesthetic emotions in games and their potential outcomes. Second, it contributes to a more nuanced understanding of positive player experience and helps to clarify concepts such as emotional challenge and character attachment. Finally, the thesis highlight game aspects that play an important role in affording aesthetic emotional experiences, and outlines avenue for future research.
This thesis addresses these research gaps in five empirical studies. Results from Publication I, Publication II, and Publication III showcase that players experience a range of aesthetic emotions in games, typically associated with other art forms. Games also afford unique aesthetic emotions, such as remorse and a sense of responsibility. Publication I and Publication III highlight that players enjoy and appreciate such aesthetic emotional experiences, in some instances, precisely because of games evoking intense negative feelings. Moreover, Publication I, Publication II, and Publication III identify means through which games facilitate aesthetic emotions, including tough decisions, as well as attachment to and loss of game characters. Players' personal experiences and memories also shape the gaming experience, highlighting how games can profoundly impact players in different ways. Notably, Publication IV showcases games' potential for affording aesthetic epistemic emotions, experiences that prompt reflection on the self and others. Finally, Publication V provides insights on how a VR game specifically designed to stimulate reflection fostered understanding and empathy for others in distress, both in-game and in real-life.
This thesis contributes to empirical and conceptual problem-solving in player-computer interaction. First, it provides empirically based descriptions of the hitherto little explored phenomenon of aesthetic emotions in games and their potential outcomes. Second, it contributes to a more nuanced understanding of positive player experience and helps to clarify concepts such as emotional challenge and character attachment. Finally, the thesis highlight game aspects that play an important role in affording aesthetic emotional experiences, and outlines avenue for future research.
2018
Alavesa, Paula
Playful appropriations of hybrid space: Combining virtual and physical environments in urban pervasive games Väitöskirja
Tietotekniikka, Oulun yliopisto., 2018, ISBN: 978-952-62-2138-0.
Abstract | Links | BibTeX | Avainsanat: englanninkieliset väitöskirjat, game user research, location-based mobile games, pervasive games, player experience
@phdthesis{Alavesa2018,
title = {Playful appropriations of hybrid space: Combining virtual and physical environments in urban pervasive games},
author = {Paula Alavesa},
url = {https://urn.fi/URN:ISBN:9789526221380},
isbn = {978-952-62-2138-0},
year = {2018},
date = {2018-01-01},
school = {Tietotekniikka, Oulun yliopisto.},
abstract = {Modern urban space, technological infrastructure, and sociability combine into a hybrid space that is the arena for urban pervasive games. Over the past two decades the changes in this game arena have been stealthy although substantial. Technological developments have helped to achieve true mobility of gaming devices, increased precision in localization, improved connectivity, and reduced orchestration required per player. Current pervasive location-based games can be played anytime anywhere. Subsequently, doors have been opened for a growing number of commercial games. These changes demand a new conceptualization of the urban game arena.
This thesis focuses on playful appropriations of hybrid space. Hybrid space is urban space that entails ubiquitous technologies. Therefore, playful appropriations of hybrid space are always, to some extent, digital as well as urban. Prior research has identified two metaphors for urban pervasive games —true mobility and true sociability. This thesis proposes an additional metaphor, called synchronicity, for binding together different realities in pervasive games. They can be anything from mirror world like realistic virtual environments, such as 3D virtual representations of a city, to abstract realities, such as the backstory of the game, or the space identity of a certain location. While location awareness is an important binding factor between the virtual and physical worlds in pervasive gameplay, synchronizable elements can be anything from encouraged collocated gameplay to semantic similarities between the combined realities.
This thesis is based on five game constructs that have been specifically designed and implemented as pervasive research games. Research data has been collected and analyzed with a mixed methods approach from field trials conducted in the wild. Constructive research is complemented with a literature review that maps the characteristics of current location-based mobile games and the game space. The main contribution of this thesis is the identification of the digital, abstract, and physical layers of reality in digital urban pervasive games. The second contribution is the identification and categorization of the synchronizable elements that bind these realities together. This thesis offers initial insights into translating this knowledge into the design of future pervasive games.},
keywords = {englanninkieliset väitöskirjat, game user research, location-based mobile games, pervasive games, player experience},
pubstate = {published},
tppubtype = {phdthesis}
}
Modern urban space, technological infrastructure, and sociability combine into a hybrid space that is the arena for urban pervasive games. Over the past two decades the changes in this game arena have been stealthy although substantial. Technological developments have helped to achieve true mobility of gaming devices, increased precision in localization, improved connectivity, and reduced orchestration required per player. Current pervasive location-based games can be played anytime anywhere. Subsequently, doors have been opened for a growing number of commercial games. These changes demand a new conceptualization of the urban game arena.
This thesis focuses on playful appropriations of hybrid space. Hybrid space is urban space that entails ubiquitous technologies. Therefore, playful appropriations of hybrid space are always, to some extent, digital as well as urban. Prior research has identified two metaphors for urban pervasive games —true mobility and true sociability. This thesis proposes an additional metaphor, called synchronicity, for binding together different realities in pervasive games. They can be anything from mirror world like realistic virtual environments, such as 3D virtual representations of a city, to abstract realities, such as the backstory of the game, or the space identity of a certain location. While location awareness is an important binding factor between the virtual and physical worlds in pervasive gameplay, synchronizable elements can be anything from encouraged collocated gameplay to semantic similarities between the combined realities.
This thesis is based on five game constructs that have been specifically designed and implemented as pervasive research games. Research data has been collected and analyzed with a mixed methods approach from field trials conducted in the wild. Constructive research is complemented with a literature review that maps the characteristics of current location-based mobile games and the game space. The main contribution of this thesis is the identification of the digital, abstract, and physical layers of reality in digital urban pervasive games. The second contribution is the identification and categorization of the synchronizable elements that bind these realities together. This thesis offers initial insights into translating this knowledge into the design of future pervasive games.
This thesis focuses on playful appropriations of hybrid space. Hybrid space is urban space that entails ubiquitous technologies. Therefore, playful appropriations of hybrid space are always, to some extent, digital as well as urban. Prior research has identified two metaphors for urban pervasive games —true mobility and true sociability. This thesis proposes an additional metaphor, called synchronicity, for binding together different realities in pervasive games. They can be anything from mirror world like realistic virtual environments, such as 3D virtual representations of a city, to abstract realities, such as the backstory of the game, or the space identity of a certain location. While location awareness is an important binding factor between the virtual and physical worlds in pervasive gameplay, synchronizable elements can be anything from encouraged collocated gameplay to semantic similarities between the combined realities.
This thesis is based on five game constructs that have been specifically designed and implemented as pervasive research games. Research data has been collected and analyzed with a mixed methods approach from field trials conducted in the wild. Constructive research is complemented with a literature review that maps the characteristics of current location-based mobile games and the game space. The main contribution of this thesis is the identification of the digital, abstract, and physical layers of reality in digital urban pervasive games. The second contribution is the identification and categorization of the synchronizable elements that bind these realities together. This thesis offers initial insights into translating this knowledge into the design of future pervasive games.