Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity

TL;DR

This paper demonstrates that using contextualized embeddings of first-person pronouns from neural language models improves the prediction of depression severity from psychotherapy text data, surpassing frequency-based methods.

Contribution

It introduces the use of contextualized first-person pronoun embeddings for depression prediction, advancing beyond traditional frequency analysis methods.

Findings

Contextualized embeddings outperform frequency-based analysis.

Embeddings improve depression severity prediction accuracy.

First-person pronoun usage context is crucial for mental health assessment.

Abstract

Prior work has shown that analyzing the use of first-person singular pronouns can provide insight into individuals' mental status, especially depression symptom severity. These findings were generated by counting frequencies of first-person singular pronouns in text data. However, counting doesn't capture how these pronouns are used. Recent advances in neural language modeling have leveraged methods generating contextual embeddings. In this study, we sought to utilize the embeddings of first-person pronouns obtained from contextualized language representation models to capture ways these pronouns are used, to analyze mental status. De-identified text messages sent during online psychotherapy with weekly assessment of depression severity were used for evaluation. Results indicate the advantage of contextualized first-person pronoun embeddings over standard classification token embeddings and frequency-based pronoun analysis results in predicting depression symptom severity. This suggests contextual representations of first-person pronouns can enhance the predictive utility of language used by people with depression symptoms.