Abstract
Self-compassion, which refers to compassion directed toward oneself, is associated with mental health and well-being. Traditionally, self-compassion has been measured and quantified using rating scales such as the Self-Compassion Scale (SCS) and Compassionate Engagement and Action Scales (CEAS). In recent years, interest in quantifying psychology using text described by people and state-of-the-art natural language processing methods, such as BERT, has increased. In this study, short open-ended free texts were collected from participants asking about their thoughts (general thoughts and those about themselves and others) and behaviors in three challenging situations. Then, a regression model was developed to predict the self-compassion scores (i.e., SCS and CEAS) from free texts with BERT. The self-compassion scores quantified by free texts and BERT highly correlated with the SCS score and certain criterion-related validity. Furthermore, the results suggest that thoughts, behaviors, and levels of self-compassion differ across situations and that the SCS score is related to both cognition (thoughts) and behaviors. The method of psychological quantification using free text may be less prone to priming or bias than measurement using questionnaires. Thus, future studies are encouraged to apply this natural-language-based approach to more diverse samples and other psychological constructs.