Skip to main content
ABCT 2023 Annual Convention Main banner
Final Program


Program Flipbook
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Ticketed Session
Ticketed Session
Recorded Session
Recorded Session
Back
ViewAttendees 12

Symposia

Adult Depression

Session: The Role of Positive Emotions in Depression and Anxiety: Evidence of Positivity Avoidance and Treatment Implications

1 - (SYM 60) Semantic Signals in Self-reference: The Detection and Prediction of Depressive Symptoms from the Daily Diary Entries of a Sample with Major Depressive Disorder

Saturday, November 18, 2023
10:30 AM – 12:00 PM PST
Location: Elwha B, Level 5

Depressed individuals experience fewer positive and more negative emotions, and use fewer positive words to describe themselves. Natural language processing (NLP) techniques have been used to predict depression, with pronoun usage and positive and negative emotions being identified as important features. However, it is unclear whether use of positive and negative words when referring to oneself can classify depression and predict depression severity using NLP. 

In the current study, 51 individuals (Mage = 38.34, SDage = 9.85; 86% female; 22% identified as a race other than White; 12% Hispanic or Latino) diagnosed with major depressive disorder through structured clinical interviews completed ecological momentary assessments, which included a mobile-friendly Patient Health Questionnaire-9 (PHQ-9) and text-based daily diary entries. Using NLP techniques, word affect, and emotion intensity lexicon, we generated 20 model features to detect and predict average weekly depression from 316 diary entries. We utilized four independent, tree-based, and cross-validated machine learning models and used SHapely Additive exPlanations to evaluate relative importance of each model feature. Two regression models detected and predicted total PHQ-9 score, and two classification models detected and predicted moderate to severe depression (PHQ-9≥10).

The models explained 22% and 15% of the variance in same-week and next-week PHQ-9 scores, respectively. Additionally, the models significantly classified current and future depression (AUC=0.72 and AUC=0.68, respectively). These results suggest that (i) lower joy intensity, (ii) higher sadness intensity, (iii) lower valence of passages with “I”/“me” as the subject, and (iv) increased usage of “I”/“me”/“my” all influence model predictions towards more severe depression.

These findings support prior research indicating that depressed individuals use fewer positive intensity words, more negative intensity words, and more first-person pronouns in their writing. Moreover, this work highlights that depressed individuals use less positive and more negative words when referring to themselves. Positive affect treatments and digital interventions, including written components, may be beneficial for targeting these linguistic features of depression.