Emotion Tracking for Remote Conferencing Applications using Neural Networks.
Paul Smith and Sam Redfern
MetadataShow full item record
This item's downloads: 626 (view details)
Paul Smith and Sam Redfern (2010) Emotion Tracking for Remote Conferencing Applications using Neural Networks AICS
In face-to-face work, discussion and negotiation relies strongly on non-verbal feedback, which provides important clues to negotiation states such as agreement/disagreement and understanding/confusion, as well as indicating the emotional states and reactions of those around us. With the continued rise of virtual teams, collaborative work increasingly requires tools to manage the reality of distributed and remote work, which is often hampered by a lack of social cohesion and such phenomena as participants multi-tasking rather than paying full attention. This paper discu sses the use of a neural network-based emotion recognition system and describes its application to the monitoring of presence and emotional states of participants in virtual meetings. Experimental analysis shows our Emotion Tracking Agent (ETA) to have marginally better accuracy at recognising universal emotions than human subjects presented with the same data.