Automatic implicit motive codings are at least as accurate as humans’ and 99% faster.
August Nilsson, J. Malte Runge, Adithya V Ganesan, Carl Viggo N G Lövenstierne, Nikita Soni, Oscar Kjell · Journal of Personality and Social Psychology · 2025
< .001, ϕ = .69). Using topic and word embedding analyses, we found specific language associated with each motive to have a high face validity. We argue that these models can be used in addition to, or instead of, human coders. We provide a free, user-friendly framework in the established R-package text and a tutorial for researchers to apply the models to their data, as these models reduce the coding time by over 99% and require no cognitive effort for coding. We hope this coding automation will facilitate a historical implicit motive research renaissance. (PsycInfo Database Record (c) 2025 APA, all rights reserved).