The AffRooms project and dataset studies the spatiotemporal relationship between affect and architectural form. Using a spatiotemporal navigation task as elicitor, the AffRooms dataset collects time-continuous affect annotations and matches the changes in affect between rooms with properties of the rooms. So far, results show that certain features of the 3D spaces (such as curvature and complexity) strongly influence the arousal levels of the viewers.
Emmanouil Xylakis, Antonios Liapis and Georgios N. Yannakakis: "Architectural Form and Affect: A Spatiotemporal Study of Arousal," in Proceedings of the IEEE International Conference on Affective Computing and Intelligent Interaction, 2021. PDF BibTex
Emmanouil Xylakis, Antonios Liapis, Georgios N. Yannakakis: "Affect in Spatial Navigation: A Study of Rooms," in IEEE Transactions on Affective Computing, 2024 (accepted). PDF BibTex