JMIR Publications

ABSTRACT

Background:

Text messaging is widely used by young people for communication and seeking mental health support through chat-based helplines. However, written communication lacks of nonverbal cues, which can be challenging for counselors to build and sustain a therapeutic relationship. Language usage is an important source of information about a person’s mental health state, and is already known to be a marker for psychopathology, specifically depression.

Objective:

The aim of the study was to investigate language usage and gender differences within a chat counseling service for adolescents and young adults.

Methods:

For the purpose of this study, anonymized chat content in the period between May 2020 and July 2021 of a German messenger-based psychosocial chat counselling service for children and adolescents (“krisenchat”) was analyzed. In total, N = 661,131 messages of N = 6,962 users were evaluated using the Linguistic Inquiry and Word Count (LIWC), considering the linguistic variables: 1st person singular and 1st person plural personal pronouns, negations, positive and negative emotion words, insight words, and words indicating causation. In addition to a descriptive analysis of those variables, gender differences were evaluated. Finally, a binary logistic regression analysis examined the predictive value of linguistic variables on the presence of psychiatric symptoms.

Results:

Across all analyzed chats, 1st person singular pronouns were used most frequently (11.6%), followed by positive emotion words (4.9%), insight words (4.1%), negations (3.8%), negative emotion words (3.2%), words indicating causation (2.9%) and, finally, 1st person plural pronouns (0.6%). Female users and users identifying as diverse used significantly more 1st person singular pronouns, negations and insight words than male users (all p < .001). Negative emotion words were used more frequently by female users than by male users or users identifying as divers (p < .001). The regression model of predicting psychiatric symptoms by linguistic variables was significant and indicated that an increased use of 1st person singular pronouns (OR = 1.05), negations (OR = 1.11), and negative emotion words (OR = 1.15) was positively associated with the presence of psychiatric symptoms, whereas an increased use of 1st person plural pronouns (OR = .04) and words indicating causation (OR = 0.90) was negatively associated with the presence of psychiatric symptoms in the users. Mainly, suicidality, self-harm and depression showed the most significant correlations to linguistic variables.

Conclusions:

This study highlights the chances of examining linguistic features in chat counseling contexts. By integrating psycholinguistic findings into counseling practice, counselors may better understand users’ psychological processes and provide a more targeted support. For instance, certain linguistic features, such as a high use of 1st person singular pronouns, negations or negative emotion words, may indicate the presence of psychiatric symptoms, particularly among female users and users identifying as diverse. Lastly, changes in language, such as reduced negations and increased positive emotion words, may indicate an improvement of a users’ mental health state and a positive effect of the counseling. Clinical Trial: DRKS00026671