SEWA Project

The Automatic Sentiment Analysis in the Wild (SEWA) is a EC H2020 funded project. The main aim of SEWA is to deploy and capitalise on existing state-of-the-art methodologies, models and algorithms for machine analysis of facial, vocal and verbal behaviour, and then adjust and combine them to realise naturalistic human-centric human-computer interaction (HCI) and computer-mediated face-to-face interaction (FF-HCI).

This will involve development of computer vision, speech processing and machine learning tools for automated understanding of human interactive behaviour in naturalistic contexts. The envisioned technology will be based on findings in cognitive sciences and it will represent a set of audio and visual spatiotemporal methods for automatic analysis of human spontaneous (as opposed to posed and exaggerated) patterns of behavioural cues including continuous and discrete analysis of sentiment, liking and empathy.

SEWA will draw on expertise from several disciplines as illustrated in the table below:

Expertise ICL UP RealEyes PlayGen
Image processing Yes Yes
Speech recognition Yes
Audio processing Yes Yes
Online learning Yes Yes Yes
Unsupervised learning Yes Yes
User studies Yes Yes Yes Yes
Multimodal learning Yes Yes
Multimodal recommendation Yes Yes
Social signals and social games Yes Yes
Audio-visual database design Yes
Ethical studies Yes Yes

Latest news


Imperial College London


Reale Eyes


University of Passau



Funding from the European Commision Horizon 2020 Programme.