Photo Sequences of Varying Emotion: Optimization with a Valence-Arousal Annotated Dataset

Mousas, Christos; Krogmeier, Claudia; Wang, Zhiquan

doi:10.1145/3458844

Cited by 3 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each image sequence included 10 images and was displayed for 4 seconds, following image presentation recommendations by Chen et al (2006), for a total of 40 s per image sequence. Please see Mousas et al (2021) for more information concerning the development of the image sequences.…”

Section: Image Sequencesmentioning

confidence: 99%

“…The OASIS dataset additionally contains normative ratings of both valence and arousal dimension of affect, collected from an online study with 822 participants (aged 18-74) in 2015, with an equal gender distribution. In our previous work (Mousas et al, 2021) we developed a system to generate image sequences with target valence and arousal values from the annotated image dataset, and validated our image sequences through a user study.…”

Section: Image Sequencesmentioning

confidence: 99%

“…used image sequences comprised of images from the Open Affective Standardized Image Set (OASIS) (Kurdi et al, 2017). These image sequences have been evaluated in a previous study (Mousas et al, 2021) in which users rated the level of arousal and valence of each image sequence. The image sequences are described in more detail in Section 2.5.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Affective Image Sequence Viewing in Virtual Reality Theater Environment: Frontal Alpha Asymmetry Responses From Mobile EEG

Krogmeier¹,

Coventry²,

Mousas³

2022

Front. Virtual Real.

View full text Add to dashboard Cite

Background: Numerous studies have investigated emotion in virtual reality (VR) experiences using self-reported data in order to understand valence and arousal dimensions of emotion. Objective physiological data concerning valence and arousal has been less explored. Electroencephalography (EEG) can be used to examine correlates of emotional responses such as valence and arousal in virtual reality environments. Used across varying fields of research, images are able to elicit a range of affective responses from viewers. In this study, we display image sequences with annotated valence and arousal values on a screen within a virtual reality theater environment. Understanding how brain activity responses are related to affective stimuli with known valence and arousal ratings may contribute to a better understanding of affective processing in virtual reality.Methods: We investigated frontal alpha asymmetry (FAA) responses to image sequences previously annotated with valence and arousal ratings. Twenty-four participants viewed image sequences in VR with known valence and arousal values while their brain activity was recorded. Participants wore the Oculus Quest VR headset and viewed image sequences while immersed in a virtual reality theater environment.Results: Image sequences with higher valence ratings elicited greater FAA scores than image sequences with lower valence ratings (F [1, 23] = 4.631, p = 0.042), while image sequences with higher arousal scores elicited lower FAA scores than image sequences with low arousal (F [1, 23] = 7.143, p = 0.014). The effect of valence on alpha power did not reach statistical significance (F [1, 23] = 4.170, p = 0.053). We determined that only the high valence, low arousal image sequence elicited FAA which was significantly higher than FAA recorded during baseline (t [23] = −3.166, p = 0.002), suggesting that this image sequence was the most salient for participants.Conclusion: Image sequences with higher valence, and lower arousal may lead to greater FAA responses in VR experiences. While findings suggest that FAA data may be useful in understanding associations between valence and arousal self-reported data and brain activity responses elicited from affective experiences in VR environments, additional research concerning individual differences in affective processing may be informative for the development of affective VR scenarios.

show abstract

Section: Image Sequencesmentioning

confidence: 99%

Section: Image Sequencesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Affective Image Sequence Viewing in Virtual Reality Theater Environment: Frontal Alpha Asymmetry Responses From Mobile EEG

Krogmeier¹,

Coventry²,

Mousas³

2022

Front. Virtual Real.

View full text Add to dashboard Cite

show abstract

Procedural Game Level Design to Trigger Spatial Exploration

Acevedo

Choi

Liu

et al. 2022

Proceedings of the 17th International Conference on the Foundations of Digital Games

View full text Add to dashboard Cite

Synthesizing Game Levels for Collaborative Gameplay in a Shared Virtual Environment

Liu

Choi

Kao

et al. 2023

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

We developed a method to synthesize game levels that accounts for the degree of collaboration required by two players to finish a given game level. We first asked a game level designer to create playable game level chunks. Then, two artificial intelligence (AI) virtual agents driven by behavior trees played each game level chunk. We recorded the degree of collaboration required to accomplish each game level chunk by the AI virtual agents and used it to characterize each game level chunk. To synthesize a game level, we assigned to the total cost function cost terms that encode both the degree of collaboration and game level design decisions. Then, we used a Markov-chain Monte Carlo optimization method, called simulated annealing, to solve the total cost function and proposed a design for a game level. We synthesized three game levels (low, medium, and high degrees of collaboration game levels) to evaluate our implementation. We then recruited groups of participants to play the game levels to explore whether they would experience a certain degree of collaboration and validate whether the AI virtual agents provided sufficient data that described the collaborative behavior of players in each game level chunk. By collecting both in-game objective measurements and self-reported subjective ratings, we found that the three game levels indeed impacted the collaboration gameplay behavior of our participants. Moreover, by analyzing our collected data, we found moderate and strong correlations between the participants and the AI virtual agents. These results show that game developers can consider AI virtual agents as an alternative method for evaluating the degree of collaboration required to finish a game level.

show abstract

Photo Sequences of Varying Emotion: Optimization with a Valence-Arousal Annotated Dataset

Cited by 3 publications

References 66 publications

Affective Image Sequence Viewing in Virtual Reality Theater Environment: Frontal Alpha Asymmetry Responses From Mobile EEG

Affective Image Sequence Viewing in Virtual Reality Theater Environment: Frontal Alpha Asymmetry Responses From Mobile EEG

Procedural Game Level Design to Trigger Spatial Exploration

Synthesizing Game Levels for Collaborative Gameplay in a Shared Virtual Environment

Contact Info

Product

Resources

About