CCSR

[Translate to English:] Virtual Mirror - (c) Zuse Institute Berlin

It has been consistently found that humans tend to copy aspects of other people’s behavior (ie “behavioral matching”, “behavioral or emotional contagion”, “automatic imitation” “chameleon effect”) in social situations. Such copying of behavior is thought to be important for the outcome of social interactions. Our approach aims to understand the mechanisms underlying such “social resonance”. Within a DFG-funded nationwide interdisciplinary Priority Project (Cooperation of cognitive science, computer science & robotics), we aim to use real time machine learning on biosignals to predict and influence social interactions in meaningful ways. To accomplish this, data of social interactions between real-time animated avatars and humans is collected. Biosignals data collection over the internet includes video and speech, later we will also collect EMG, eye tracking and thermal imaging in the lab. We work closely with the Berlin based ZIB who provide technically advanced avatars with lifelike visual- and action- features that can be manipulated in meaningful expressive ways.

Our approach promises better understanding of (large-scale and interactive) “social resonance” phenomena – e.g., positive collective emotions (online, face-to-face), or more problematic phenomena such as social exclusion or the propagation of hate speech. Furthermore, it will increase the effectiveness of avatar communication by giving them social abilities. Overall, CCSR aims to evolve and test theories on social resonance, and to lay the necessary technical foundations for fruitful application of real time social resonance for human-computer interaction.

CCSR

The Cognitive Control of Social Resonance (CCSR)