Automatic Analyses of Human Behaviour (PGT) PSYCH5091

  • Academic Session: 2023-24
  • School: School of Psychology and Neuroscience
  • Credits: 10
  • Level: Level 5 (SCQF level 11)
  • Typically Offered: Semester 2
  • Available to Visiting Students: No

Short Description

Nonverbal behaviours are known to have a powerful influence on human interaction as well as interactions between humans and artificial agents. They convey a large quantity of information linked to communicative intentions but also other traits and mental states that influence an interaction in ways that participants may not even be aware of that can transform how the interaction unfolds as well as the beliefs, emotions and attitudes that arise. When interacting with humans, social artificial agents are often endowed with such meaningful and expressive nonverbal behaviours.

Timetable

10 hours of lecture for 5 weeks

Requirements of Entry

Typically a 2:1 honours degree in psychology or related discipline.

Excluded Courses

None

Assessment

Individual 3,500 word report.

Course Aims

In this course, we will present computational methods to incorporate expressive behaviours in agents. We will start by providing an overview of how traits and mental states are expressed multi-modally. The focus will be on communicative acts as well as emotions, social attitudes and metaphors and in turn how facial expression, gaze, posture and gesture convey this information. We will then explore a variety of automated methods and tools to model what nonverbal behaviours to perform and how to realise them in an embodied agent.

Intended Learning Outcomes of Course

By the end of this course students will be able to:

• Critically evaluate the complex interaction of traits, mental states and behaviour in social interaction.

• Model mental states in social interaction including from both sides of an interaction.

• Model the relation of traits and states to nonverbal behaviour and synthesizing/animating those behaviours.

• Reflect critically on methods to realize models: annotating schemes for behaviour; mocap; Keyframe;   animation and procedural techniques for synthesizing behaviour; crowd-sourcing and Machine Learning Techniques. 

• Critically evaluate approaches to realizing behaviour in social interaction.

• Understand how to use the tools used to create embodied agents.

Minimum Requirement for Award of Credits

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.