Xiyuan Gao

Xiyuan Gao is an external researcher at Campus Fryslân, Graduate School, University of Groningen (RUG), Netherlands. Their research focuses on pragmatic language understanding in human-machine interaction, particularly multimodal sarcasm detection using textual, audio, and visual cues.

Gao's work explores how prosodic variation, semantic incongruity, and facial expressions can be modeled to understand language beyond literal content. Key research areas include pragmatic computing, affective computing, and the development of computational models for sarcasm that account for emotional and cultural context.

Recent publications (2024-2025) demonstrate a focus on deep learning approaches, such as graph attention networks and attention-based fusion, for multimodal sarcasm detection. The research emphasizes the functional trade-offs between different modalities and the role of emotional incongruity, with applications in improving human-machine interaction.