The field of human-computer interaction is witnessing a significant shift towards nonverbal communication, with a growing emphasis on developing systems that can understand and generate emotional cues. Researchers are exploring the potential of non-photorealistic characters, robotic displays, and interactive infographics to convey emotions and facilitate more effective human-computer interaction. Studies have shown that incorporating nonverbal cues, such as gestures and facial expressions, can enhance user engagement and trust in human-robot collaboration. However, detecting miscommunication in human-robot dialogue remains a significant challenge, with current machine learning models struggling to accurately identify errors. Noteworthy papers in this area include:

• A study on co-speech gesture and facial expression generation for non-photorealistic 3D characters, which proposed methods for expressing emotions using expression data extracted from comics and dialogue-specific semantic gestures.
• A paper on deception detection in dyadic exchanges using multimodal machine learning, which demonstrated the efficacy of integrating data from both the deceiver and the deceived to detect deception in interactions.