Mohammad Soleymani
Creative Technologies (United States), University of Southern California
Papers
5
Total Citations
85
H-Index
4
About
Mohammad Soleymani is a researcher whose work sits at the dynamic intersection of affective computing, human-robot interaction, and multimodal behavioral analysis. His research investigates how machines can perceive, interpret, and respond to human emotions and social cues, with a particular focus on the computational understanding of nonverbal and verbal behavior. Among his most influential contributions is his cross-corpus analysis of human reactions to robot conversational failures (31 citations), which shed critical light on how people respond multimodally when robots break down in task-oriented dialogues — a key challenge in deploying socially intelligent systems. His work on multimodal analysis of intimate self-disclosure (29 citations) further demonstrated how verbal and nonverbal signals can be computationally modeled to support mental health applications, bridging affective computing and psychological well-being. Soleymani has also advanced semi-supervised affective adaptation techniques through metric learning frameworks, addressing the persistent challenge of limited labeled data in emotion recognition. Beyond research, he has made notable strides in AI accessibility and education, developing an open-source robot-building curriculum (17 citations) designed to make AI learning engaging and inclusive for K-12 and college students — reflecting a commitment to broadening participation in AI literacy.
Research Focus
Key Achievements
Top Papers
- 1
- 2Multimodal Analysis and Estimation of Intimate Self-Disclosure29 citations · 2019
- 3
- 4
- 5