TY - JOUR
T1 - Assessing ML classification algorithms and NLP techniques for depression detection
T2 - An experimental case study
AU - Lorenzoni, Giuliano
AU - Tavares, Cristina
AU - Nascimento, Nathalia
AU - Alencar, Paulo
AU - Cowan, Donald
N1 - Publisher Copyright:
© 2025 Lorenzoni et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2025/5
Y1 - 2025/5
N2 - Context and background. Depression has affected millions of people worldwide and has become one of the most common mental disorders. Early mental disorder detection can reduce costs for public health agencies and prevent other major comorbidities. Additionally, the shortage of specialized personnel is very concerning since depression diagnosis is highly dependent on expert professionals and is time-consuming. Research problems. Recent research has evidenced that machine learning (ML) and natural language processing (NLP) tools and techniques have significantly benefited the diagnosis of depression. However, there are still several challenges in the assessment of depression detection approaches in which other conditions such as post-traumatic stress disorder (PTSD) are present. These challenges include assessing alternatives in terms of data cleaning and pre-processing techniques, feature selection, and appropriate ML classification algorithms. Purpose of the study. This paper tackles such an assessment based on a case study that compares different ML classifiers, specifically in terms of data cleaning and pre-processing, feature selection, parameter setting, and model choices. Methodology. The experimental case study is based on the Distress Analysis Interview Corpus - Wizard-of-Oz (DAIC-WOZ) dataset, which is designed to support the diagnosis of mental disorders such as depression, anxiety, and PTSD. Major findings. Besides the assessment of alternative techniques, we were able to build models with accuracy levels around 84% with Random Forest and XGBoost models, which is significantly higher than the results from the comparable literature which presented the level of accuracy of 72% from the SVM model. Conclusions. More comprehensive assessments of ML classification algorithms and NLP techniques for depression detection can advance the state of the art in terms of improved experimental settings and performance.
AB - Context and background. Depression has affected millions of people worldwide and has become one of the most common mental disorders. Early mental disorder detection can reduce costs for public health agencies and prevent other major comorbidities. Additionally, the shortage of specialized personnel is very concerning since depression diagnosis is highly dependent on expert professionals and is time-consuming. Research problems. Recent research has evidenced that machine learning (ML) and natural language processing (NLP) tools and techniques have significantly benefited the diagnosis of depression. However, there are still several challenges in the assessment of depression detection approaches in which other conditions such as post-traumatic stress disorder (PTSD) are present. These challenges include assessing alternatives in terms of data cleaning and pre-processing techniques, feature selection, and appropriate ML classification algorithms. Purpose of the study. This paper tackles such an assessment based on a case study that compares different ML classifiers, specifically in terms of data cleaning and pre-processing, feature selection, parameter setting, and model choices. Methodology. The experimental case study is based on the Distress Analysis Interview Corpus - Wizard-of-Oz (DAIC-WOZ) dataset, which is designed to support the diagnosis of mental disorders such as depression, anxiety, and PTSD. Major findings. Besides the assessment of alternative techniques, we were able to build models with accuracy levels around 84% with Random Forest and XGBoost models, which is significantly higher than the results from the comparable literature which presented the level of accuracy of 72% from the SVM model. Conclusions. More comprehensive assessments of ML classification algorithms and NLP techniques for depression detection can advance the state of the art in terms of improved experimental settings and performance.
UR - http://www.scopus.com/inward/record.url?scp=105006850108&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=105006850108&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0322299
DO - 10.1371/journal.pone.0322299
M3 - Article
C2 - 40435349
AN - SCOPUS:105006850108
SN - 1932-6203
VL - 20
JO - PloS one
JF - PloS one
IS - 5 May
M1 - e0322299
ER -
