Friend or Foe: A Review and Synthesis of Computational Models of the Identity Labeling Problem

ABSTRACT

We introduce the identity labeling problem – given an individual in a social situation, can we predict what identity(ies) they will be labeled with by someone else? This problem remains a theoretical gap and methodological challenge, evidenced by the fact that models of social-cognition often sidestep the issue by treating identities as already known. We build on insights from existing models to develop a new framework, entitled Latent Cognitive Social Spaces, that can incorporate multiple social cues including sentiment information, socio-demographic characteristics, and institutional associations to estimate the most culturally expected identity. We apply our model to data collected in two vignette experiments, finding that it predicts identity labeling choices of participants with a mean absolute error of 10.9%, a 100% improvement over previous models based on parallel constraint satisfaction and affect control theory.

KEYWORDS:

• social identity
• social psychology
• computational social science
• analytical sociology

Notes

¹ For a discussion of how BayesACT, ACT’s successor, can be similarly used, see Appendix A.

² We included a manipulation check for the connection of these names to the associated ages by asking respondents how old they expected someone named “Ethel”, “Harold”, “Brittany” and “Johnny” to be. Our expectation was that Harold and Ethel would be of nearly equivalent age, and that this age would be appropriate for an elderly individual. We also expected that Johnny and Brittany would also be of a roughly equivalent age, and that this age would correspond roughly to the age of a child. On average, Ethel was expected to be around 73 years old; Harold around 60, Brittany around 29 and Johnny around 30. This suggests that the manipulation check worked better for the older identities than the younger identities, because they are much closer to the stages in the life-course we were intending. More importantly, however, is that there is a much larger lifecourse difference between age the participants reported for Harold and Ethel and those reported for Johnny and Brittany.