Despite the advances in Affective Computing, the application of affect models is still narrowly limited to answering questions like: "What is the mental state of patients while interacting with a robot?", "What emotions does an advertisement elicit in viewers?", "What is an actor's emotion in a scene?" or "What is the user's emotional state while playing a game?". From the above, it becomes apparent that affect models are context-dependent and cannot answer questions like "Why do these emotional states appear?" or "What are the elements of the context that cause the specific emotions?". The next generation of affect models should be context-invariant and able to identify and exploit cause-effect relations in humans’ emotional manifestation. ERICA is an ambitious project that aims to design affect models that use the ubiquitous cause-effect mechanisms in humans’ emotional expression.
The main challenges that hinder the development of causation-aware affect modelling algorithms are:
ERICA proposes a holistic approach for causal affect modelling ranging from the identification of high-level causal predictors in affect modelling, up to developing modular models of affect based on the identified cause-effect mechanisms.
ERICA addresses fundamental research questions in affect modelling. Its results will serve for ground-breaking technological advances in affective computing and emotion-aware artificial intelligence.
Objective 1: Discover and identify causal and anti-causal high-level affect predictors. The first objective aims to introduce a rigorous methodology for discovering and identifying high-level features describing the interaction's context and user's measurements that are causally related to emotions. Through that ob- jective, ERICA makes a significant step towards bringing causation into affect modelling
Objective 2: Develop modular models of affect using transferable cause-effect relations. The next gener- ation of affect models should generalise across a range of environments by reusing components that ap- pear robust and invariant across contexts and users. ERICA aims to derive reusable/transferable mecha- nisms of emotion manifestation and build, for the first time, general affect models, that is, models trained on a specific environment but capable of generalising across a range of environments.
The research outcomes of the ERICA project will be published here.
This project has received funding from the Malta Council for Science & Technology (MCST) under grant agreement REP-2023-36.