Seminar Affective Computing for Empathic Behaviour Change

This is a hybrid teaching unit, it will partially be held online, partially in class.

How would your computer respond if you looked frustrated, upset or stressed? Could your phone comfort you if you were sad after getting a call? Could your smart home adjust the music, lighting, or other aspects of the environment around you after you’ve had a bad day at work — without being asked?[1] Can your computer offer you help if it sees you stressed without the need of your assistance?
Emotions and empathy have always been a fundamental part of the human experience but only recently they have started to be considered in the development of interactive technologies in order to create computers that can recognise a range of subtle human emotions, behave in an empathic way and adapt to the human’s emotional state (i.e. stress conditions, etc.).

The goal of this seminar is to study some of the latest advances in emotion recognition and emphatic behaviour change as well as emphatic companions. Moreover responses generally and empathic responses specifically will be studied. In this context a special case is considered which is “stress”, a body and mental effect that we face daily. Two types of stress exist: the negative known as distress and the positive one known as eustress.

Empathy is the capacity to understand or feel what another person is experiencing from within the other person’s frame of reference, i.e., the capacity to place oneself in another’s position [2], [3]. Despite there are still many definitions for empathy that encompass a broad range of emotional states, nowadays there is considerable agreement in the research community that empathy consists of three different aspects [4]: recognizing someone else’s emotional state (i.e., cognitive empathy), the convergence of feelings between people (i.e., emotional convergence), and responding to another person’s (inferred) feelings or the emotional convergence those feelings initiate (i.e., empathic responding).

Stress is a tension and pressure felt in the body that might be affecting positively or negatively our mental and physical health. By mental health we mean our emotional state, mood and behaviour, by physical health we mean the body, diet, weight and sleep etc. Stress is affecting every individual so what are the advantages of positive stress, and disadvantages of negative stress? What are the effects that can be seen in the body? What type of emotions can induced by stress, can it change our mood and behaviour?

Human emotions recognition is a complex task, stress is much more complex as well. Body and face temperature change, facial expressions, body language and voice tone, all these are examples of features related to the emotional state and stress reactional effects of a person.

This seminar will investigate how we can recognize human emotion and stress (using facial expression, physiological signals, etc.) and design interactive technologies and empathic companions to enhance quality of life and support the user during their daily activities (e.g. reduce cumulative stress at work, boost positive stress to increase performances, manage stress in semi-autonomous driving, etc.). This seminar will help the students to improve their research and practical abilities. It will have a strong practical component as students will investigate existing applications as well as develop new concepts in the aforementioned domains.


Code 33822
Type Seminar
Site Fribourg
Track(s) T3 – Advanced Information Processing
T6 – Data Science
Semester A2020


Learning Outcomes
  • Identify and illustrate existing approaches in emotion recognition and empathetic interaction.
  • Discuss and compare different methods for emotions recognition along with their strengths and weaknesses.
  • Study stressful situations and behaviour of a person.
  • Define emotions that can be induced by stress.
  • Research changes in the psychological and physiological behaviour and mood.
  • Identify and describe different kinds of physiological signals that can be used for emotion recognition and stress identification.
  • Identify the main components of an emphatic systems.
  • Evaluate and select the best existing systems to design and implement a complete emotion recognition system based on physiological signals.
  • Research methods and algorithms that are available to reduce stress.
Lecturer(s) Denis Lalanne
Elena Mugellini
Omar Abou Khaled
Language english
Course Page

The course page in ILIAS can be found at

Schedules and Rooms

Period On Appointment
Location UniFR, PER21 / online


Evaluation type continuous evaluation

Additional information


First Lecture
Please contact Elena Mugellini ( to select the date of the first meeting.

[1] Forbes Journa,
[2] Bellet, Paul S.; Michael J. Maloney (1991). “The importance of empathy as an interviewing skill in medicine”. JAMA. 226 (13): 1831–1832. doi:10.1001/jama.1991.03470130111039.
[3] Wikipedia,
[4] Decety J, Lamm C (2007) The role of the right temporoparietal junction in social interaction: how low-level computational processes contribute to meta-cognition. Neuroscientist 13(6):580–593
[5] Shalom Greene, Himanshu Thapliyal, Allison Caban-Holt A survey of affective computing for stress detection: Evaluating technologies in stress detection for better health, IEEE Consumer Electronics Magazine (Volume: 5 , Issue: 4 , Oct. 2016)