[3D4-OS-20a] OS-20

[3D4-OS-20a-03] User Sentiment Estimation During Dialogue Using Meta-Learning Method

〇Tatsushi Miura¹, Daiki Tokieda¹, Shogo Okada¹ (1. Japan Advanced Institute of Science and Technology)

Keywords:sentiment estimation, dialogue system, machine learning, multimodal signal processing, social signal processing

For more natural and smooth interactions between humans and computers, a model that can predict a person's internal state from multiple modalities of information and generate appropriate responses accordingly is desirable. However, current multimodal dialogue systems face challenges such as the high cost of dataset collection and noise caused by variations in data due to users' personality traits. In this study, we apply the meta-learning method called Model-Agnostic Meta-Learning (MAML) to the multimodal sentiment estimation task to verify its effectiveness in addressing these challenges. As a result, we demonstrate that MAML achieves higher accuracy in predicting the internal states of dialogue system users compared to existing methods in multimodal sentiment estimation.