Celso M. de Melo

US Army Research Laboratory West
12015 Waterfront Drive, Building #3
Playa Vista, CA 90094

demelo@usc.edu

1. People Are Fairer When Acting Via Agents
Increasingly autonomous agents act on our behalf in health, finance, driving, defense, etc. This research suggests people tend to adopt a broader, higher-ob_get_level perspective when programming these agents and, thus, act more fairly when compared to direct interaction. Read the paper.
2. People Do Not Feel Guilty About Exploiting Machines
This research shows that we experience emotions differently with machines, when compared to humans. Specifically, people feel less guilt when exploiting machines, but just as much envy when being exploited. This helps explain why people decide differently with machines. Read the paper.
3. Reading People's Minds From Emotion Expressions
Emotion expressions can be windows into other people's minds. This research shows that people make inferences about how others are appraising the ongoing interaction from emotion expressions and, from this information, about others' beliefs, desires, and intentions. Read the paper.
Bootstrap Slider

I am interested in creating machines that show the kind of intelligence we see in humans. For over 15 years, I have (a) created computational systems that support multimodal expression via face, body, and words, (b) developed cognitive (or AI) models of complex human behavior (e.g., emotion), and (c) explored new media and pushed the boundaries of human-machine interaction (e.g., augmented/virtual reality). My work has practical implications in health, social training, education, games, robotics, etc.

I recently joined the Army Research Lab West as a Computer Scientist. My research will continue to focus on human-machine interaction, artificial intelligence, and virtual/augmented reality.

Previously, I finished a postdoc at the USC Marshall School of Business with Peter Carnevale. This research was funded by an NSF Grant and focused on:

  • The interpersonal effects of emotion expression on people's decision making and corresponding implications for the design of intelligent human-computer interaction systems;
  • Virtual humans, or three-dimensional characters that look and act like humans, as a computational interface for the future and a basic research tool for the behavioral sciences;
  • How perceptions of cognitive and affective ability in others influences decision making and its consequences for human-computer and computer-mediated decision making.

I earned my Ph.D. in Computer Science at the University of Southern California. This work consisted of creating cognitive computational models of emotion and decision making using various artificial intelligence techniques (e.g., machine learning). This work was done at the Institute for Creative Technologies with Jonathan Gratch.

Previously, I received a M.Sc. in Computer Science at the Technical University of Lisbon (IST) with Ana Paiva at the Synthetic Characters and Intelligent Agents Group (GAIPS). There, I began developing my virtual humans framework that supports multimodal expression through face, gesture, and voice.

I was born in beautiful Mozambique and also am proud to be Portuguese.

 

Last updated: September 6th, 2017