|SCOTTI VINCENZO||Cycle: XXXV |
Section: Computer Science and Engineering
Tutor: PRADELLA MATTEO
Advisor: SBATTELLA LICIA Major Research topic
:Empathetic Conversational AgentAbstract:
The research work included in this thesis aims at exploring the possibilities of empathy in human-computer interaction through a social conversational agent. The peculiarity of this research stands in the choice of going beyond simple “emotional resonance” in the response, leveraging a more complex, multilevel empathic mechanism as driver for the generation of the reply. Through this multi-level architecture, which will help to provide an effective strategy for social interaction, we expect to achieve a long-term deep-engagement with the user. Emotion will still play an important role in the interaction, and for this reason we selected voice as main communication channel with the agent. In fact voice isn’t just the most natural communication channel, but also because -along with text- permits to modulate interaction, to detect emotions and moods, and thus facilitates the creation of an “empathetic interaction” between user and machine. As voice, and hence language, will be the main communication channels, we are completing the empathic stack with one sub layer (the physical one, mainly working on prosody) and one over layer (semantic, related to the content of the interaction). The underling architecture of the resulting chatbot will be a combination of traditional model-driven Artificial Intelligence (AI) solutions for Natural Language Processing (NLP) and more recent data-driven solutions based on Deep Neural Networks (DNN). With this hybrid agent, together with the empathic response stack, we aim at getting rid of the “rigidity” characterizing current systems, which will surely result in a better user experience.