Affect Control Processes (Bayesian Affect Control Theory)

Affect Control Theory (ACT) arises from a tradition of symbolic interactionism in sociology. Bayesian Affect Control Theory (or BayesACT for short) generalises ACT by introducing explicit notions of uncertainty and utility. BayesACT accounts for the dynamic fluctuation of identity meanings for self and other during interactions, elucidates how people infer and adjust meanings through social experience, and shows how stable patterns of interaction can emerge from individuals' uncertain perceptions of identities. BayesACT may be used in an active inference framework, giving policies of action in which social prescriptions are anticipatory, and both guide (create), and are guided by, sensory inputs. BayesACT has been applied in an intelligent tutoring system, a social dilemma game player, an assistant for persons with Alzheimer's disease, and in sentiment analysis. We've got more projects on the go, check back for updates!

See also:

Demonstrative Videos for the 2021 paper: Citizens Madmen and Children.
You can watch a series of video lectures introducing Affect Control Theory and Bayesact here.
Watch my talk at the Vector Institute on affective computing - see the talk video and see a shorter interview video
Also see the instructional and simulation videos below.
You can watch Areej Alhothali's talk at NAACL/HLT 2015 on sentiment analysis using ACT.
You can watch the 2017 ACT Conference videos here or here.
  • BayesACT project on GitHub. Current version is 2.3.8. Email Jesse for access if you want access.
  • Code from Hoey MacKinnon Schroeder JDM 2021 article.