This page presents basic info about automatic scoring of mindreading in childhood and early adolescence.
The page is part of a WELLCOME project awarded to Dr. Rory T. Devine at the University of Birmingham.
Mindreading (or Theory of Mind, ToM) is the ability to understand others' thoughts, feelings, and desires. It has garnered substantial interest in psychological research since the early 1980s. Continued curiosity about ToM can perhaps be explained by three factors:
Research over the past decade has demonstrated both ongoing development in mindreading beyond early childhood across middle childhood and adolescence (e.g., Weimer et al., 2021) and the presence of early emerging and stable individual differences in mindreading (e.g., Devine, 2021).
Mmeta-analyses of case-control studies indicate that, rather than being limited to conditions such as autism (e.g., Rødgaard et al., 2019), ToM deficits cross-cut a wide range of psychological and developmental conditions including, for example, schizophrenia (e.g., Chung et al., 2014), mood disorders (e.g., Bora and Berk, 2016), and specific language impairment (e.g., Nilsson and López, 2016)
Accumulating evidence indicates that normative individual differences in mindreading are socially meaningful in that children who excel at tests of ToM are more popular than their peers (Slaughter et al., 2015), more likely than their peers to show prosocial behavior (Imuta et al., 2016), and more socially skilled than their peers in everyday social interactions (e.g., Devine et al., 2016).
Our own contribution to the research on mindreading and the automatic scoring of mindreading in childhood and early adonecense can be found in:
Kovatchev, V., Smith, P., Lee, M, and Devine, R., “Can Vectors Read Minds Better Than Experts? Comparing Data Augmentation Strategies for the Automated Scoring of Children’s Mindreading Ability” at Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2021
Kovatchev, V., Smith, P., Lee, M, Grumley Traynor, I., Luque Aguilera, I., and Devine, R., “What is on your mind?” Automated Scoring of Mindreading in Childhood and Early Adolescence at Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020
We have trained a machine learning algorithm for scoring the Strange Story Task and the Silent Film Task.
You can download the python code for scoring from GitHub
We also have a web-based solution where you can use our model to automatically score your data (for English).
If you want to use the web-based solution, please contact Dr. Rory T. Devine for the web address and instructions for use.