11:15   Oral Session 8-KzZ - Emotional Synthetic Characters 2
Chair: Catherine Pelachaud
11:15
25 mins 		Integration of a semantic and affective model for realistic generation of emotional states in virtual characters
Diana Arellano, Isaac Lera, Javier Varona, Francisco J. Perales
Abstract: In this paper we proposed a computational model that automatically integrates a knowledge base with an affective model. The knowledge base presented as a semantic model, is used for an accurate definition of the emotional interaction of a virtual character and their environment. The affective model generates emotional states from the emotional output of the knowledge base. Visualization of emotional states is done through facial expressions automatically created using the MPEG-4 standard. In order to test the model, we designed a story that provides the events, preferences, goals, and agent's interaction, used as input for the model. As a result the emotional states obtained as output were totally coherent with the input of the model. Then, the facial expressions representing these states were evaluated by a group of persons from different academic backgrounds, proving that emotional states can be recognized in the face of the virtual character.
11:40
25 mins 		“I can feel it too!”: Emergent empathic reactions between synthetic characters.
Sérgio Hortas Rodrigues, Samuel Francisco Mascarenhas, João Dias, Ana Paiva
Abstract: Empathy is often seen as the capacity to perceive, understand and experience others’ emotions. This concept has been incorporated in virtual agents to achieve better believability, social interaction and user engagement. However, this has been mostly done to achieve empathic relations with the users. Instead, in this article we focus on empathy between synthetic characters and propose an analytical approach that consists in a generic computational model of empathy, supported by recent neuropsychological studies. The proposed model of empathy was implemented into an affective agent architecture. To evaluate the implementation a small scenario was defined and we asked a group of users to visualize it with the empathy model and another group to visualize it without the model. The results obtained confirmed that our model was capable of producing significant effects in the perception of the emergent empathic responses.
12:05
25 mins 		Effects of Emotional Agents on Human Players in the Public Goods Game
Katharina Göttlicher, Sabine Stein, Dirk M. Reichardt
Abstract: In previous work we chose the public goods game as a small and adequate example scenario for emotional agents. In our experiment we focus on the influence of emotional reactions of the virtual agents on a human player. The artificial emotions of the agents are generated by a model of emotion which is adapted to the scenario. In our experiment we compare the reactions of the human player in a scenario with and without visual feedback of the other agents. As a visual feedback we use the ECA Greta to embody the emotions generated by our model. An adequate emotion recognition could be proven by an online survey validating the correct valence and intensity perception of the relevant emotions. As one of the first results, a significantly higher amount of investment can be stated for the human player in case he or she sees the facial representation of the emotional state of the other (virtual) players during the public goods game. After splitting up the game in two sections, it could be shown that this significant difference is only given for the second part of the game.