"What is on your mind?" Automated Scoring of Mindreading in Childhood and Early Adolescence
This work addresses the need for scalable assessment of social cognition in developmental psychology, though it is incremental as it applies existing NLP methods to a new domain.
The researchers tackled the problem of automated scoring of mindreading ability in children aged 7-14 by creating MIND-CA, a corpus of 11,311 question-answer pairs from 1,066 children, and obtained promising results using state-of-the-art NLP solutions.
In this paper we present the first work on the automated scoring of mindreading ability in middle childhood and early adolescence. We create MIND-CA, a new corpus of 11,311 question-answer pairs in English from 1,066 children aged 7 to 14. We perform machine learning experiments and carry out extensive quantitative and qualitative evaluation. We obtain promising results, demonstrating the applicability of state-of-the-art NLP solutions to a new domain and task.