The relationship between news content and its presentation has been a long-studied problem in the communications domain. Often, channels with a relatively smaller audience create a more powerful impact by amplifying the intensity of their content through a marked (usually biased) manner of presentation. SuperGlue Kinesics is a step in the direction of the investigation of this relationship and its influence on the public at large.
SuperGlue Kinesics is a media analyzer that fuses multiple modalities to create a comprehensive model for the cross-analysis of facial expressions, body gestures, posture, scene context, and other nonverbal cues in broadcast news. We explore the nature of news portrayal on different media outlets to understand how they affect their audiences and contribute to the formation of potentially dangerous "echo chambers."