Estimation of Psychological Distress in Japanese Youth Through Narrative Writing: Text-Based Stylometric and Sentiment Analyses

Abstract

Background Internalizing mental illnesses associated with psychological distress are often underdetected. Text-based detection using natural language processing (NLP) methods is increasingly being used to complement conventional detection efforts. However, these approaches often rely on self-disclosure through autobiographical narratives that may not always be possible, especially in the context of the collectivistic Japanese culture. Objective We propose the use of narrative writing as an alternative resource for mental illness detection in youth. Accordingly, in this study, we investigated the textual characteristics of narratives written by youth with psychological distress; our research focuses on the detection of psychopathological tendencies in written imaginative narratives. Methods Using NLP tools such as stylometric measures and lexicon-based sentiment analysis, we examined short narratives from 52 Japanese youth (mean age 19.8 years, SD 3.1) obtained through crowdsourcing. Participants wrote a short narrative introduction to an imagined story before completing a questionnaire to quantify their tendencies toward psychological distress. Based on this score, participants were categorized into higher distress and lower distress groups. The written narratives were then analyzed using NLP tools and examined for between-group differences. Although outside the scope of this study, we also carried out a supplementary analysis of narratives written by adults using the same procedure. Results Youth demonstrating higher tendencies toward psychological distress used significantly more positive (happiness-related) words, revealing differences in valence of the narrative content. No other significant differences were observed between the high and low distress groups. Conclusions Youth with tendencies toward mental illness were found to write more positive stories that contained more happiness-related terms. These results may potentially have widespread implications on psychological distress screening on online platforms, particularly in cultures such as Japan that are not accustomed to self-disclosure. Although the mechanisms that we propose in explaining our results are speculative, we believe that this interpretation paves the way for future research in online surveillance and detection efforts.

Exploring the use of AI text-to-image generation to downregulate negative emotions in an expressive writing application

“…As such, we have yet to evaluate the application in cultures and languages outside of the English-speaking US. Because StoryWriter’s textual input is fictional and anonymous, not demanding the disclosure of personal, traumatic incidents (as in conventional expressive-writing-based therapies), we expect that the tool will be particularly accessible to individuals from East-Asian countries, who are often uncomfortable with self-disclosure [ 52 , 65 ]. More research is recommended to appraise the tool’s efficacy for emotion regulation outside of Anglo-American contexts.…”

“…Instead, we opted to use a story-based expressive writing task that allows users to submit fictional narratives. Participants were instructed to ‘write the introduction of a short story’ and to ‘describe its setting and place while being as imaginative as possible’ (see [ 52 ]). They were also instructed to write for a set period of time (three minutes for Study 1, five minutes for Study 2).…”

Leveraging stylometry analysis to identify unique characteristics of peer support user groups in online mental health forums

“…Tokens have been popularly used in stylometry analysis 24 . We also measured the impact of emotion-related words that have been found to be significant in identifying different levels of mental illness 25 . An emotion-related word is the word that is associated with one or more than particular emotions, such as happiness, sadness, anger or fear.…”

“…Stylometry analysis has been proven to be an effective tool in identifying and understanding the writing styles and linguistic patterns of individuals 24 . For example, it has been used to identify psychological distress levels of youth individuals by examining some stylometric features in their narrative writings 25 . Stylometric features are characteristics of an individual’s writing style that can be quantified and analysed using computational methods.…”

“…Our study explores different types of stylometric features, including ‘emotion-related’ words, ‘pronouns’, and ‘unigrams’ and their use by different groups of forum users. Previous research has shown that unigrams are commonly used 24 , while emotion-related words have been found to provide important insights into the emotional states of people experiencing mental health challenges 25 . Likewise, pronouns have often demonstrated importance in understanding emotional states 26 .…”